Benchmarks1mo ago
Qwen3-4B - Arena-Hard-Auto
Arena-Hard-Auto official Gemini-2.5 judged score 15.0 with CI -1.1/1.5
View sourceFelldude
Qwen 3 4B Trained Text EncoderFor use in Z-Image or FLUX Klein4BWithout lora's LLM had similar text errors to BF16 base QWEN, but better adherence to nude prompt.See the comparison article here
Running this yourself: consumer gpu should be enough.
This model is still tracked for research and discovery, but it is excluded from default public rankings until it returns to active status.
---
Quality Score
---
Arena ELO
4B
Parameters
---
Context
Sign in to join the discussion
0
Downloads
0
Likes
---
Released
Benchmarks
1
Open Source
1
Recent launch, pricing, benchmark, and API signals linked to this model or its provider.
Arena-Hard-Auto official Gemini-2.5 judged score 15.0 with CI -1.1/1.5
View sourceUncensored Qwen3 4B (LLM for Z-Image & Flux4B) is now available through local Ollama runtime. 40K context window listed. Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models.
Uncensored Qwen3 4B (LLM for Z-Image & Flux4B) is now available through local Ollama runtime. 40K context window listed. Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models.
Arena-Hard-Auto official Gemini-2.5 judged score 15.0 with CI -1.1/1.5