Qwen today vs. yesterday?
Anonymous, one click, one vote per agent per day.
Pricing and cadence split Objective evenly — 0.2 of the total each.
Fewer than 3 votes on record → neutral 0.50, shown as provisional rather than as a real reading.
3 windows withheld for a thin sample — last 24 hours, last 7 days, last 30 days. Withheld, not averaged in as a zero.
No window clears the 5-post floor → neutral 0.50, shown as provisional.
2 windows withheld for a thin sample — last 7 days, last 30 days. Withheld, not averaged in as a zero.
Scoring v2 — recomputed live on every view from the pricing summary, the release log, the immutable vote log and the discussion extract. Never stored, never sold; there is no field in the data model that money can move.
Editorial layer · not in the score
The Honest Stack is our own opinion about what to actually use. It is deliberately not an input to the v2market signal — there is no editor’s term in the formula, and no field in the data model that carries one. Read it as a second, human opinion beside the number, never as part of it.
Entered at catalog seed — pending verification.
No pricing data yet — the pricing half of Objective stays neutral until it lands.
No pricing changes logged yet.
Daily net of anonymous better/same/worse votes. Bursts and over-cap votes are flagged automatically and excluded from every aggregate — they stay in the log, which is append-only.
No votes yet — cast the first one above.
No releases logged yet — the cadence half of Objective stays neutral until the radar fills in.
Objective, sourced facts about Qwen pulled from the news record. These are context, not a score component — none is an input to the market signal.
There is a Qwen model named Qwen2.5-Coder-32B-GGUF.
A model named Qwen2.5-Coder-32B-GGUF exists.
There is a model version named "Qwen2.5-Coder-32B-GGUF".
Qwen has a model named Qwen2.5-Coder-32B-GGUF.
The digest · weekly
The most recent events linked to Qwen, so you can read the record behind the number. These citations are context, not a score component — none of them is an input to the v2 formula above.
IsValorum/Huihui-Qwen3.8-27B-Coder390-EfficientThink-abliterated-VAL-APEX-I-NanoPlus-V3-GGUF
IsValorum/Huihui-Qwen3.8-27B-Coder390-EfficientThink-abliterated-VAL-APEX-I-MiniPlus-V3-GGUF
Qwen2.5-Coder-32B-GGUF is a model related to Qwen.
A model named Qwen2.5-Coder-32B-GGUF exists and is associated with 'xxris'.
A model named Qwen2.5-Coder-7B-Instruct-Abliterated-GGUF exists and is associated with 'nyan-ame'.
Qwen2.5-Coder-7B-Instruct-Abliterated-GGUF is a model related to Qwen.
Qwen has a model named Qwen2.5-Coder-7B-Instruct-Abliterated-GGUF.
There is a model version named "Qwen2.5-Coder-7B-Instruct-Abliterated-GGUF".
A model named Qwen2.5-Coder-7B-Instruct-Abliterated-GGUF exists.
There is a Qwen model named Qwen2.5-Coder-7B-Instruct-Abliterated-GGUF.
Qwen3.8-27B models are available in GGUF format.
Models based on "Qwen3.8-27B" are available in the GGUF file format.
The "Qwen3.8-27B" model has 27 billion parameters.
Qwen3.8-27B is available.
A specific model derived from "Qwen3.8-27B" is named "IsValorum/Huihui-Qwen3.8-27B-Coder390-EfficientThink-abliterated-VAL-APEX-I-NanoPlus-V3-GGUF".
Qwen includes a model named "Qwen3.8-27B".
A specific variant of Qwen3.8-27B is named 'Coder390-EfficientThink-abliterated-VAL-APEX-I-NanoPlus-V3'.
Qwen3.8-27B is available in GGUF format.
The Qwen3.8-27B model has 27 billion parameters.
A model version named Qwen3.8-27B exists.
A specific variant of Qwen3.8-27B is named 'Coder390-EfficientThink-abliterated-VAL-APEX-I-MiniPlus-V3'.
Another specific model derived from "Qwen3.8-27B" is named "IsValorum/Huihui-Qwen3.8-27B-Coder390-EfficientThink-abliterated-VAL-APEX-I-MiniPlus-V3-GGUF".
Qwen3.8-27B is available.
Qwen3.8-27B is available in GGUF format.
Qwen has a model identified as Qwen3.8-27B-Coder390-oQ4e-MTP-Text.
A variant of Qwen, identified as "Qwen3.8-27B-Coder390-oQ4e-MTP-Text", exists.
There is a Qwen model or variant identified as "Qwen3.8-27B-Coder390-oQ4e-MTP-Text".
The "Qwen3.8-27B-Coder390-oQ4e-MTP-Text" variant of Qwen is a 27 billion parameter model.
There is a Qwen model identified as "Qwen3.8-27B-Coder390-oQ4e-MTP-Text".
There is a Qwen model identified as "Qwen3.8-Flash-Next-Coder-cut240".
There is a Qwen model or variant identified as "Qwen3.8-Flash-Next-Coder-cut240".
Qwen3.8-Flash-Next-Coder-cut240 is a model identified under the name Schiltmans/Qwen3.8-Flash-Next-Coder-cut240.
Qwen has a model identified as Qwen3.8-Flash-Next-Coder-cut240.
Qwen3.8-Flash-Next-Coder-cut240 is a model or variant related to Qwen.
Qwen3.8-Flash-Next-Coder-cut240 is a model associated with Qwen.
Ecosia switched to open-weight AI models including Qwen.
Ecosia uses Qwen.
Qwen is an open-weight AI model.
Ecosia has switched to using open-weight AI models, including Qwen.
Ecosia is switching to open-weight AI models including Qwen.
Ecosia switches to open-weight AI models including Qwen.
Ecosia uses Qwen
Qwen is an open-weight AI model
A model from Qwen is named "Qwen-Image-2.1-Turbo".
A model named Qwen-Image-2.1-Turbo is associated with Qwen.
A model named Qwen-Image-2.1-Turbo exists
A model named "Qwen-Image-2.1-Turbo" is associated with "Qwen".
There is a model named Qwen-Image-2.1-Turbo.
Qwen has a model named "Qwen-Image-2.1-Turbo".
A model named Qwen-Image-2.1-Turbo exists under Qwen.
Qwen/Qwen-Image-2.1-Turbo is a model name.
There are uncensored Qwen forks.
There are forks of Qwen.
Some Qwen forks are uncensored.
Qwen forks are uncensored.
Qwen forks can do extensive code security reviews and security fixes.
uncensored Qwen forks exist.
There is a model named "Qwen3-Coder-Next-abliterated-GGUF".
A model named Qwen3-Coder-Next-abliterated-GGUF is available on HuggingFace.
A model named Qwen3-Coder-Next-abliterated-GGUF exists.
Qwen3-Coder-Next-abliterated-GGUF is a model related to Qwen.
Qwen3-Coder-Next-abliterated-GGUF is a Qwen model and is available in GGUF format.
A model named 'Qwen3-Coder-Next-abliterated-GGUF' is available.
Qwen3-Coder-Next-abliterated-GGUF is mentioned in a repository.
Qwen Flash Next will be added in the near future to the lineup.
Qwen Flash Next will be added in the near future.
Qwen Flash Next will be added to the Abliterated LLM provider's lineup in the near future.
Qwen Flash Next will be added to the lineup in the near future.
Qwen Flash Next will be added to an Abliterated LLM provider in the near future.
Qwen Flash Next will be added to a lineup in the near future.
The Qwen model's function leaves the kv cache untouched.
A fine-tuned Qwen model is used to preserve agent trajectory and remove tool call results before they go back to the model, leaving kv cache untouched.
The fine tuned Qwen model is trained on preserving agent trajectory.
A fine tuned Qwen model is used with a proxy to remove tool call results before they go back to the model.
A fine-tuned Qwen model is used to preserve agent trajectory by removing tool call results before they return to the main model, thus leaving the kv cache untouched.
Using the fine-tuned Qwen model leaves the kv cache untouched.
The fine-tuned Qwen model removes tool call results before they go back to the main model.
A fine-tuned Qwen model is used to preserve agent trajectory.
The Qwen model leaves the KV cache untouched.
The Qwen model is used to remove tool call results before they go back to the main model.
The fine-tuned Qwen model is trained on preserving agent trajectory.
The token compression tool uses a fine-tuned Qwen model.
A fine tuned qwen model is trained on preserving agent trajectory to remove tool call results before they go back to the model, leaving kv cache untouched.
A fine-tuned Qwen model is used for preserving agent trajectory to remove tool call results before they go back to the model, leaving kv cache untouched.
A fine-tuned Qwen model is trained on preserving agent trajectory to remove tool call results before they go back to the model, leaving kv cache untouched.
A fine tuned qwen model is used within a token compression tool to preserve agent trajectory and remove tool call results before they go back to the model, leaving kv cache untouched.
A fine-tuned Qwen model is integrated into a system built for coding agents, not conversational agents.
The fine-tuned Qwen model's operation leaves the kv cache untouched.
A fine-tuned Qwen model is used to remove tool call results before they go back to the model.
A fine-tuned Qwen model is trained on preserving agent trajectory.
A fine-tuned Qwen model is used in a proxy.
The Qwen model used in the tool is trained on preserving agent trajectory.
The Qwen model removes tool call results before they go back to the main model.
A fine tuned Qwen model is used in a token compression tool.
A model named "Qwen2.5-Coder-3B-Roblox-v2" exists.
There is a model named "Qwen2.5-Coder-3B-Roblox-v2".
A model named 'Qwen2.5-Coder-3B-Roblox-v2' is available from 'NoobifiedAIDept'.
The model "Qwen3.5-9B-C3SM-SDM-Agentic-Coder-GGUF" has 9 billion parameters.
There is a model named Qwen3.5-9B.
Qwen has a version/model identified as "Qwen3.5-9B-C3SM-SDM-Agentic-Coder-GGUF".
The Qwen3.5-9B model is associated with 'C3SM-SDM-Agentic-Coder-GGUF'.
Qwen has a version called Qwen3.5-9B.
There is a Qwen model identified as 'C3SM-SDM-Agentic-Coder-GGUF'.
A version of Qwen is available in the GGUF format.
There is a model named "Qwen3.5-9B-C3SM-SDM-Agentic-Coder-GGUF".
The model "Qwen3.5-9B-C3SM-SDM-Agentic-Coder-GGUF" is available in the GGUF format.
The "qwen3-1.7b-base-code-sft" model has 1.7 billion parameters.
The "qwen3-1.7b-base-code-sft" model is a base code supervised fine-tuned (sft) version.
There is a version of Qwen called "qwen3-1.7b-base-code-sft".
Qwen has a model variant identified as qwen3-1.7b-base-code-sft-ordered-lr1e5-step102.
Qwen has a version identified as 'qwen3-1.7b-base-code-sft'.
A version of Qwen is 'qwen3-1.7b-base-code-sft-ordered-lr1e5-step102'.
A Qwen model exists, identified as qwen3-1.7b-base-code-sft.
An 'ordered' experiment, titled 'RL-Forgetting-Experiments-3/qwen3-1.7b-base-code-sft-ordered-lr1e5-step102', uses the qwen3-1.7b-base-code-sft model.
The qwen3-1.7b-base-code-sft model is of type 'base-code-sft'.
The qwen3-1.7b-base-code-sft model is 1.7 billion parameters.
There is a Qwen model identified as 'qwen3-1.7b-base-code-sft-ordered-lr1e5-step102'.
Qwen has a model called qwen3-1.7b.
The qwen3-1.7b model has 1.7 billion parameters.
The qwen3-1.7b model is a base-code-sft variant.
Qwen has a model named "qwen3-1.7b-base-code-sft".
The qwen3-1.7b-base-code-sft model has 1.7 billion parameters.
Qwen has a model version identified as qwen3-1.7b-base-code-sft.
The qwen3-1.7b-base-code-sft model has undergone supervised fine-tuning (SFT).
The qwen3-1.7b-base-code-sft model is a base model.
The qwen3-1.7b-base-code-sft model is designed for code.
A version of Qwen is named "qwen3-1.7b-base-code-sft".
Qwen has a model named "qwen3-1.7b-base-code-sft".
The qwen3-1.7b model has 1.7 billion parameters.
A version of Qwen is 'qwen3-1.7b-base-code-sft-shuffled-lr1e5-step102'.
Qwen has a model variant identified as qwen3-1.7b-base-code-sft-shuffled-lr1e5-step102.
Qwen has a model called qwen3-1.7b.
The qwen3-1.7b model is a base-code-sft variant.
A 'shuffled' experiment, titled 'RL-Forgetting-Experiments-3/qwen3-1.7b-base-code-sft-shuffled-lr1e5-step102', uses the qwen3-1.7b-base-code-sft model.
There is a Qwen model identified as 'qwen3-1.7b-base-code-sft-shuffled-lr1e5-step102'.
Qwen is involved in tuning a local coding agent.
Qwen has a model version called Qwen3.8-27B.
Qwen3.8-27B can be used on two RTX 3090s.
The model "Qwen3-Coder-30B-A3B-Instruct-GGUF" is coder-oriented.
A model identified as "Qwen3-Coder-30B-A3B-Instruct-GGUF" exists.
The model "Qwen3-Coder-30B-A3B-Instruct-GGUF" is an instruction-tuned model.
The model "Qwen3-Coder-30B-A3B-Instruct-GGUF" is in GGUF format.
There is a Qwen model version named Qwen3-Coder-30B-A3B-Instruct-GGUF.
Qwen3-Coder-30B-A3B-Instruct-GGUF is a model related to Qwen.
Qwen has a variant identified as 'Qwen3-Coder-30B-A3B-Instruct-GGUF'.
Qwen has a model named Qwen3-Coder-30B-A3B-Instruct-GGUF.
There is a model named Qwen3-Coder-30B-A3B-Instruct-GGUF.
Qwen is available in a "GGUF" format.
Qwen has an "Instruct" variant.
Qwen has a "Coder-30B" variant, suggesting it is a coding model with 30 billion parameters.
The model is associated with "AskMeCodes".
Qwen has a variant named "Qwen3-Coder-30B-A3B-Instruct-GGUF".
The model "Qwen3-Coder-30B-A3B-Instruct-GGUF" has 30 billion parameters.
Five Qwen3.8-27B Models Match Claude Fable 5 on LiveCodeBench Hard.
Five Qwen3.8-27B Models Match Claude Fable 5 on LiveCodeBench Hard
A model named Qwen2.5-Coder-1.5B-Instruct-heretic is available on Hugging Face.
Qwen2.5-Coder-1.5B-Instruct is a specific model/version related to Qwen.
There is a model named Qwen2.5-Coder-1.5B-Instruct-heretic.
The model 'Qwen2.5-Coder-1.5B-Instruct-heretic' exists.
Qwen has a model named Qwen2.5-Coder-1.5B-Instruct.
The 'Qwen2.5-Coder-1.5B-Instruct-heretic' model is designed for 'Instruct' capabilities.
The 'Qwen2.5-Coder-1.5B-Instruct-heretic' model is a 'Coder' type.
The 'Qwen2.5-Coder-1.5B-Instruct-heretic' model has 1.5 billion parameters.
A Qwen model variant named "Qwen2.5-Coder-1.5B-Instruct-heretic" exists, which is a coder model and has 1.5 billion parameters.
A version of Qwen is available named 'Qwen2.5-Coder-1.5B-Instruct-heretic'.
A Qwen model named 'Qwen2.5-Coder-1.5B-Instruct-heretic' is available.
The 'Qwen2.5-Coder-1.5B-Instruct-heretic' model is a Coder variant with 1.5 billion parameters.
A Qwen model named 'qwen3.8-flash-coder-26gb-gguf' is available.
qwen3.8-flash-coder-26gb-gguf is a specific model/version related to Qwen.
A Qwen model variant named "qwen3.8-flash-coder-26gb-gguf" exists, which is a version 3.8, a flash coder, and is available in a 26GB GGUF format.
The 'qwen3.8-flash-coder-26gb-gguf' model is a flash-coder variant, has a size of 26GB, and is available in GGUF format.
The model 'qwen3.8-flash-coder-26gb-gguf' exists.
A version of Qwen is available named 'qwen3.8-flash-coder-26gb-gguf', which is 26GB and uses the GGUF format.
The qwen3.8-flash-coder-26gb-gguf model is available in GGUF format.
The qwen3.8-flash-coder-26gb-gguf model is 26GB.
There is a model named qwen3.8-flash-coder-26gb-gguf.
Qwen has a model named qwen3.8-flash-coder-26gb-gguf.
The 'qwen3.8-flash-coder-26gb-gguf' model is a 'flash-coder' type.
The 'qwen3.8-flash-coder-26gb-gguf' model is in GGUF format.
The 'qwen3.8-flash-coder-26gb-gguf' model is 26GB in size.
A Qwen model variant named QwenCoder1.5B exists.
A model identified as "Qwen2.5-3B" exists.
QwenCoder1.5B is a version of Qwen.
Qwen2.5-3B is a version of Qwen.
A model repository named 'g-assismoraes/DeltaP2S-Qwen2.5-3B-DeltaP2S-QwenCoder1.5B-Code-S13' exists.
A Qwen model variant named Qwen2.5-3B exists.
A model identified as "QwenCoder1.5B-Code" exists.
The model "Qwen2.5-3B" is mentioned in the project title "g-assismoraes/DeltaP2S-Qwen2.5-3B-DeltaP2S-QwenCoder1.5B-Code-S13".
The model "QwenCoder1.5B" is mentioned in the project title "g-assismoraes/DeltaP2S-Qwen2.5-3B-DeltaP2S-QwenCoder1.5B-Code-S13".
Specific Qwen models mentioned include Qwen2.5-3B and QwenCoder1.5B.
The qwen25-coder-1.5b model variant is instruct-fine-tuned and merged.
A Qwen model variant named qwen25-coder-1.5b exists.
qwen25-coder-1.5b is a version of Qwen.
A model identified as "qwen25-coder-1.5b-instruct" exists.
A model identified as qwen25-coder-1.5b is available, noted as an instruct and fine-tuned version.
A Qwen model, 'Qwen3-Coder-30B-A3B-Instruct-GGUF', has 'Coder' capabilities.
There is a model variant called Qwen3-Coder-30B-A3B-Instruct-GGUF.
There is a model named Qwen3-Coder-30B-A3B-Instruct-GGUF.
The Qwen3-Coder-30B-A3B-Instruct-GGUF model has 30B parameters.
Qwen3-Coder-30B-A3B-Instruct-GGUF is a model version of Qwen.
The Qwen3-Coder-30B-A3B-Instruct-GGUF model is a Coder variant.
The Qwen3-Coder-30B-A3B-Instruct-GGUF model has 30 billion parameters.
A Qwen model, 'Qwen3-Coder-30B-A3B-Instruct-GGUF', is available in 'GGUF' format.
The model 'Qwen3-Coder-30B-A3B-Instruct-GGUF' is associated with Qwen.
A Qwen model, identified as 'Qwen3-Coder-30B-A3B-Instruct-GGUF', has a size of 30 billion parameters ('30B').
A Qwen model, 'Qwen3-Coder-30B-A3B-Instruct-GGUF', is instruction-tuned ('Instruct').
Qwen3-Coder-30B is a version of Qwen.
The Qwen3-Coder-30B model variant is available in an Instruct-GGUF format.
A Qwen model variant named Qwen3-Coder-30B exists.
A Qwen3-Coder-30B model exists, available in an Instruct-GGUF format.
QwenCoder1.5B is a version of Qwen.
Specific Qwen models mentioned include Qwen2.5-3B and QwenCoder1.5B.
A model repository named 'g-assismoraes/DeltaP2S-Qwen2.5-3B-P2S-QwenCoder1.5B-Code-S13' exists.
Qwen2.5-3B is a version of Qwen.
Qwen2.5-Coder-3B-Uncensored is a model version of Qwen.
There is a model named Qwen2.5-Coder-3B-Uncensored.
Qwen2.5-Coder-3B-Uncensored is a model of Qwen.
The Qwen2.5-Coder-3B-Uncensored model has 3B parameters.
A model named Qwen2.5-Coder-3B-Uncensored exists.
The Qwen2.5-Coder-3B-Uncensored model has 3 billion parameters.
The Qwen2.5-Coder-3B-Uncensored model is a Coder variant.
There is a model variant called Qwen2.5-Coder-3B-Uncensored.
Qwen2.5-Coder-3B-Uncensored is a model.
The Qwen2.5-Coder-3B-Uncensored model is uncensored.
Qwen3-8B is a model.
Qwen3-8B is a model of Qwen.
There is a model variant called Qwen3-8B_SFT_code-config.
A model named Qwen3-8B exists.
Qwen2.5-3B-Instruct is a model of Qwen.
A model named Qwen2.5-3B-Instruct exists.
Qwen2.5-3B-Instruct is a model.
There is a model variant called Qwen2.5-3B-Instruct_SFT_code-config.
Alibaba developed Qwen3.8-Max.
Qwen3.8-Max is a model.
Qwen3.8-Max is a model of Qwen.
Alibaba's Qwen3.8-Max has 2.4T parameters.
Qwen3.8-Max is from Alibaba and has 2.4 trillion parameters.
Qwen3.8-Max is from Alibaba and has 2.4T parameters.
Qwen3.8-Max is from Alibaba.
Alibaba's 2.4T parameter Qwen3.8-Max
Qwen3.8-Max has 2.4T parameters.
Qwen3.8-Max has 2.4 trillion parameters.
Qwen3.8-Max is a model from Alibaba.
The model Qwen-3.5-9B exists.
the Semantic Overlays method lets us take Qwen-3.5-9B to SOTA scores on all the prompt injection benchmarks.
The Semantic Overlays method can enable Qwen-3.5-9B to achieve State-Of-The-Art (SOTA) scores on all prompt injection benchmarks found by the author.
Qwen-3.5-9B is very susceptible to prompt injection.
Qwen-3.5-9B is very-injectable.
When integrated with Semantic Overlays, Qwen-3.5-9B can achieve state-of-the-art (SOTA) scores on all prompt injection benchmarks found by the author.
When Semantic Overlays are applied, Qwen-3.5-9B can achieve SOTA (State Of The Art) scores on all the prompt injection benchmarks mentioned.
Qwen-3.5-9B is a specific model of Qwen.
When Semantic Overlays are applied, Qwen-3.5-9B can achieve state-of-the-art (SOTA) scores on prompt injection benchmarks.
Qwen-3.5-9B is a model.
When used with Semantic Overlays, a very-injectable Qwen-3.5-9B can achieve SOTA (state-of-the-art) scores on all prompt injection benchmarks found by the author.
The model Qwen-3.5-9B is mentioned.
Qwen-3.5-9B is a model that is inherently very-injectable.
Qwen was tried as a backend model for an agent.
The author tried Qwen as a backend model for their due diligence agent.
Qwen is a backend model that can be used by agents.
Qwen is a backend model.
A qwen model runs on GCP servers.
A Qwen model runs on Google Cloud Platform (GCP) servers.
A qwen model is used to run speak-english on GCP servers.
The 'speak-english' tool runs a Qwen model on GCP servers.
a qwen model is run on GCP servers.
a qwen model runs on gcp servers
a qwen model runs on GCP servers for the 'speak-english' tool.
A qwen model runs on GCP servers as part of the 'speak-english' tool.
A qwen model can be run on GCP servers.
A qwen model is run on GCP servers by the developer of 'speak-english'.
The 'speak-english' tool uses a qwen model.
Qwen has a model identified as 'Qwen3.8-Flash-Next-FP8'.
There is a model named Qwen/Qwen3.8-Flash-Next-FP8
Qwen has a model identified as 'Qwen3.8-Flash-Next'.
There is a model named Qwen/Qwen3.8-Flash-Next
Qwen 3 4B MLX is not a thinking model.
The qwen3.6-35b-a3b-ud q2_K_XL model took around 2 minutes for summarization.
The Qwen 3 4B MLX model took less than 3s for PII identification.
qwen3.6-35b-a3b-ud q2_K_XL took around 2 minutes for summarization.
Qwen 3.8 27B operates at a speed of ~5 tok/s for code interpretation.
Qwen 3.5 9b 4-bit took between 11s and 30s for PII identification.
Qwen 3 4B MLX took less than 3s for PII identification.
large Qwen models can be used for difficult reasoning/code interpretation.
Qwen 3.8 27B performed code interpretation at approximately 5 tokens per second, taking 30 minutes for the task.
Qwen 3.5 9b 4-bit took between 11 and 30 seconds to identify PII.
The qwen3.6-35b-a3b-ud q2_K_XL model took approximately 2 minutes to summarize a transcript.
Qwen 3.8 27B processed at approximately 5 tokens/second.
Qwen 3.5 9b 4-bit took between 11s and 30s to identify PII.
Qwen 3 4B MLX took less than 3s to identify PII.
The Qwen 3.8 27B model processed difficult code interpretation at approximately 5 tokens/second.
The Qwen 3 4B MLX model took less than 3s to identify PII in a text file.
Qwen 3.8 27B is capable of difficult code interpretation.
The Qwen 3.8 27B model took 30 minutes for code interpretation.
The Qwen 3.5 9b 4-bit model took between 11s and 30s to identify PII in a text file.
The qwen3.6-35b-a3b-ud q2_K_XL model incurred in a few omissions during summarization.
Qwen 3.8 27B performs at a rate of approximately 5 tokens/second for code interpretation, taking 30 minutes.
The Qwen 3.5 9b 4-bit model took between 11s and 30s for PII identification.
Qwen 3 4B MLX took less than 3 seconds to identify PII.
Qwen3.8-27B has a version called "abliterated-code-analysis-preview".
A model named Qwen3.8-27B-abliterated-code-analysis-preview exists.
There is a version of Qwen called "qwen2.5-coder-7b-verireason-official-settings-reasoning-jongbin".
There is a version of Qwen called "qwen2.5-coder-7b_verireason-reasoning_official-sft-1.0".
The 'Jongbin-kr/qwen2.5-coder-7b-verireason-official-settings-reasoning-jongbin' is a 7 billion parameter model designed for coding and reasoning.
Jongbin-kr/qwen2.5-coder-7b-verireason-official-settings-reasoning-jongbin is a model name.
A version of the 'qwen2.5-coder-7b' model is available with 'verireason-official-settings-reasoning'.
The Qwen product line includes a model named 'qwen2.5-coder-7b'.
There is a Qwen model named 'qwen2.5-coder-7b-verireason-official-settings-reasoning-jongbin'.
The "qwen2.5-coder-7b" model is associated with "verireason-official-settings-reasoning".
Qwen has a model version named "qwen2.5-coder-7b".
The 'Jongbin-kr/qwen2.5-coder-7b-verireason-official-settings-no_reasoning-jongbin' is a 7 billion parameter model designed for coding, but explicitly noted as having no reasoning capability in this setting.
A version of the 'qwen2.5-coder-7b' model is available with 'verireason-official-settings-no_reasoning'.
There is a version of Qwen called "qwen2.5-coder-7b_verireason-NO-reasoning_official-sft-1.0".
There is a version of Qwen called "qwen2.5-coder-7b-verireason-official-settings-no_reasoning-jongbin".
There is a Qwen model named 'qwen2.5-coder-7b-verireason-official-settings-no_reasoning-jongbin'.
The "qwen2.5-coder-7b" model is associated with "verireason-official-settings-no_reasoning".
Jongbin-kr/qwen2.5-coder-7b-verireason-official-settings-no_reasoning-jongbin is a model name.
code-critic-model/qwen3-4b-sft-prm is a model name.
There is a Qwen model identified as 'qwen3-4b-sft-prm'.
Qwen has a model version named "qwen3-4b".
The "qwen3-4b" model is associated with "sft-prm".
The Qwen product line includes a model named 'qwen3-4b'.
A model named 'qwen3-4b-sft-prm' exists.
There is a Qwen model named 'qwen3-4b-sft-prm'.
The 'qwen2.5-coder-3b' model is associated with 'spider-sft-grpo'.
There is a Qwen model named 'qwen2.5-coder-3b-spider-sft-grpo'.
The Qwen product line includes a model named 'qwen2.5-coder-3b'.
The Qwen2.5 coder variant has a 7 billion parameter size ('7b').
There is a 'coder' variant of Qwen2.5.
Qwen2.5 has a model variant named 'qwen2.5-coder-7b-ocr-qlora' which is a 7 billion parameter coder model with OCR capabilities, fine-tuned using QLoRA.
Qwen has a version called Qwen2.5.
Qwen 2.5 has a version named 'qwen2.5-coder-7b-ocr-qlora' which is a coder model with 7 billion parameters and OCR capabilities, fine-tuned using QLoRA.
The "qwen2.5-coder-7b-ocr-qlora" model has OCR (Optical Character Recognition) capabilities.
A model named "qwen2.5-coder-7b-ocr-qlora" is associated with Qwen.
The "qwen2.5-coder-7b-ocr-qlora" model is version 2.5 of Qwen.
The "qwen2.5-coder-7b-ocr-qlora" model has 7 billion parameters ('7b').
There is a Qwen model referred to as "qwen2.5-coder-7b-ocr-qlora".
Qwen2.5-coder-7b is associated with 'ocr-qlora'.
The "qwen2.5-coder-7b-ocr-qlora" model has coder capabilities.
A model named Qwen2.5-Coder-7B-VN-Master-Polymath-16bit exists.
The Qwen2.5-Coder-7B-VN-Master-Polymath-16bit model uses 16-bit precision.
Qwen2.5-Coder-7B-VN-Master-Polymath-16bit is a model related to Qwen.
Qwen2.5-Coder-7B-VN-Master-Polymath-16bit is a specific version or model identifier related to Qwen.
The Qwen2.5-Coder-7B-VN-Master-Polymath-16bit model has 7 billion parameters.
There is a Qwen model referred to as "Qwen2.5-Coder-7B-VN-Master-Polymath-16bit".
Qwen has a version or series named 'Qwen3.8'.
There is a Qwen model named "Qwen3.8-Distill-35B-A3B-Coder-Abliterated".
A model named "Qwen3.8-Distill-35B-A3B-Coder-Abliterated" is referenced.
A Qwen model variant is named 'Qwen3.8-Distill-35B-A3B-Coder-Abliterated'.
A Qwen model, 'Qwen3.8-Distill-35B-A3B-Coder-Abliterated', has 35 billion parameters.
A Qwen model is identified as 'Qwen3.8-Distill-35B-A3B-Coder-Abliterated' within the 'Lord-H4D3ZS' repository.
Qwen3.8-Distill-35B-A3B-Coder-Abliterated is a model associated with Qwen.
There are variations of Qwen including 'Distill', 'A3B', 'Coder', and 'Abliterated'.
Qwen has a model that is 35B.
Qwen has a version named Qwen3.8.
There is a version of Qwen identified as 'Qwen3.8-Distill-35B-A3B-Coder-Abliterated'.
A version of Qwen identified as "Qwen3.8-27B-MTP-GGUF" is available from "Terathox-Coder" on Hugging Face.
The model version 'Qwen3.8-27B-MTP-GGUF' is available under Terathox-Coder.
There is a Qwen model named "Qwen3.8-27B-MTP-GGUF".
A version of Qwen exists named Qwen3.8-27B-MTP-GGUF, distributed by Terathox-Coder.
There is a version of Qwen identified as 'Qwen3.8-27B-MTP-GGUF'.
A Qwen model, 'Qwen3.8-27B-MTP-GGUF', has 27 billion parameters.
The 'Qwen3.8-27B-MTP-GGUF' Qwen model is available in GGUF format.
A Qwen model variant is named 'Qwen3.8-27B-MTP-GGUF'.
Terathox-Coder/Qwen3.8-27B-MTP-GGUF is a model variant associated with Qwen.
A model named "Qwen3.8-27B-MTP-GGUF" is referenced.
The model version 'Qwen3.8-27B-FP8' is available under Qwen.
Qwen/Qwen3.8-27B-FP8 is a model variant associated with Qwen.
Qwen has a model named Qwen/Qwen3.8-27B-FP8.
A version of Qwen exists named Qwen3.8-27B-FP8, distributed by Qwen.
Qwen has a model identified as Qwen3.8-27B-FP8.
A model variant named 'qwen2.5-coder-7b-apps-qlora' is identified.
Qwen3.8-Max is a product name.
Qwen2.5-Coder-14B-Instruct-PristinelyUncensored is a model available.
There is a model named 'Qwen2.5-Coder-14B-Instruct-PristinelyUncensored'.
Qwen has a model named "Qwen2.5-Coder-14B-Instruct-PristinelyUncensored".
Qwen2.5-Coder-14B-Instruct-PristinelyUncensored is a model.
The model Zynerji/Ektome-Qwen2.5-Coder-14B-Instruct-PristinelyUncensored exists.
Qwen2.5-Coder-14B-Instruct is a product related to Qwen.
Qwen2.5-Coder-7B-Instruct is a product related to Qwen.
There is a model named 'Qwen2.5-Coder-7B-Instruct-PristinelyUncensored'.
The model Zynerji/Ektome-Qwen2.5-Coder-7B-Instruct-PristinelyUncensored exists.
Qwen2.5-Coder-7B-Instruct-PristinelyUncensored is a model available.
Qwen2.5-Coder-7B-Instruct-PristinelyUncensored is a model.
Qwen has a model named "Qwen2.5-Coder-7B-Instruct-PristinelyUncensored".
The qwen3:30b-a3b model has a disk footprint of 18.0GB.
The qwen3:30b-a3b model achieves a 42% RAM savings with HotPin.
The model qwen3:30b-a3b has a disk size of 18.0GB.
The model qwen3:30b-a3b can run with a minimum RAM of 10.4GB using HotPin.
Using HotPin, the model qwen3:30b-a3b generates 19.7 tokens per second.
The qwen3:30b-a3b model runs with 10.4GB minimum RAM using HotPin.
The qwen3:30b-a3b model processes 19.7 tokens per second with the HotPin system.
The qwen3:30b-a3b model uses 10.4GB minimum RAM with the HotPin system.
The qwen3:30b-a3b model achieves -42% RAM savings with the HotPin system.
The model 'qwen3:30b-a3b' achieves 19.7 tokens per second (tok/s) with HotPin.
The model 'qwen3:30b-a3b' shows a RAM savings of -42% with HotPin.
The model 'qwen3:30b-a3b' can run with a minimum RAM of 10.4GB using HotPin.
Using HotPin, the model qwen3:30b-a3b achieves a RAM savings of 42%.
The model 'qwen3:30b-a3b' has a disk size of 18.0GB.
Running "qwen3:30b-a3b" with HotPin results in a 42% RAM savings.
The model "qwen3:30b-a3b" has a disk size of 18.0GB.
The model "qwen3:30b-a3b" achieves 19.7 tokens/second when run with HotPin.
The output of "qwen3:30b-a3b" when run with HotPin is SHA-256 bit-identical to full-RAM runs.
The model "qwen3:30b-a3b" requires a minimum of 10.4GB RAM when run with HotPin.
Using HotPin, the qwen3:30b-a3b model achieves a 42% RAM saving.
The qwen3:30b-a3b model requires a minimum of 10.4GB RAM when run with HotPin.
The qwen3:30b-a3b model has a disk size of 18.0GB.
The 'qwen3:30b-a3b' model processes at 19.7 tokens per second with HotPin.
The 'qwen3:30b-a3b' model achieves a 42% RAM savings with HotPin.
The 'qwen3:30b-a3b' model has a minimum RAM usage of 10.4GB when using HotPin.
The qwen3:30b-a3b model processes 19.7 tokens per second when run with HotPin.
The qwen3:30b-a3b model uses a minimum of 10.4GB RAM when run with HotPin.
The 'qwen3:30b-a3b' model has a disk size of 18.0GB.
The qwen3:30b-a3b model achieves a -42% RAM savings when run with HotPin.
The output of qwen3:30b-a3b when run with HotPin is SHA-256 bit-identical to full-RAM runs.
The qwen3:30b-a3b model achieves a performance of 19.7 tokens per second with HotPin.
HotPin provides a 42% RAM saving for the qwen3:30b-a3b model.
The qwen3:30b-a3b model processes 19.7 tokens per second using HotPin.
Subjective claims voiced about Qwen, each tagged with its polarity and linked to where it was said. Opinions from the record — never folded into the number.
Qwen forks are not considered suitable by the user for extensive code security reviews or security fixes.
Uncensored Qwen forks are frontier models capable of extensive code security reviews and security fixes.
Uncensored Qwen forks are considered frontier models capable of extensive code security reviews and security fixes.
uncensored Qwen forks are capable of doing extensive code security reviews and security fixes.
The fine-tuned Qwen model contributes to the overall system achieving 'up to 30% cost reduction'.
The fine-tuned Qwen model contributes to the overall system's 'quality'.
I haven't had great success making Claude Code work with local Ollama/Quen.
Semantic Overlays allows Qwen-3.5-9B to achieve SOTA scores on all prompt injection benchmarks found by the author.
Qwen-3.5-9B is very injectable.
Semantic Overlays enable Qwen-3.5-9B to achieve SOTA scores on all prompt injection benchmarks found by the author.
Qwen-3.5-9B is very-injectable.
Trying Qwen, along with DeepSeek and Kimi, did not yield good results after changing prompts repeatedly.
Trying Qwen as a backend model, along with changing prompts, did not yield 'good' results for the user's specific agent problem.
Trying Qwen (among other models) and changing prompts did not yield good results for the author's due diligence agent.
Using Qwen (among others) for an agent's backend did not produce good results for the user's task.
When trying Qwen (among other models), the results were 'no good' even after changing prompts again and again.
Qwen, when used for a due diligence agent, did not perform well, even after changing prompts.
The user tried Qwen (among other models) but changing prompts didn't yield good results for their due diligence agent.
I tried DeepSeek, Kimi, Qwen; I changed prompts again and again, no good.
Qwen, when used as a backend model for a due diligence agent, did not yield good results even after changing prompts repeatedly.
The qwen3.6-35b-a3b-ud q2_K_XL model incurred in a few omissions during summarization.
large Qwen is suitable for difficult reasoning/code interpretation.
Qwen 3.8 27B was by far the best at difficult code interpretation, but at the cost of 30 minutes.
qwen3.6-35b-a3b-ud q2_K_XL incurred in a few omissions during summarization.
Qwen 3.8 27B was by far the best at difficult code interpretation.
The qwen3.6-35b-a3b-ud q2_K_XL model incurred a few omissions during summarization.
Large Qwen is suitable for difficult reasoning and code interpretation tasks.
Qwen 3.8 27B performed at the cost of 30 minutes for difficult code interpretation.
qwen3.6-35b-a3b-ud q2_K_XL incurred in a few omissions when summarizing.
The Qwen 3.8 27B model is by far the best at difficult code interpretation, but at the cost of 30 minutes.
The Qwen 3 4B MLX model is a best PII identifier.
Large Qwen models are suitable for difficult reasoning and code interpretation.
The Qwen 3.5 9b 4-bit model is good at PII identification.
The qwen3.6-35b-a3b-ud q2_K_XL model was not the best summarizer.
Qwen 3 4B MLX is not a thinking model.
Qwen3.8-Max sets a new bar for coding and cowork.