Uncensored Qwen3.8-Flash-Next Vision Model Released in GGUF
orcarouter · hf · 2026-08-29
An uncensored version of the Qwen model, Qwen3.8-Flash-Next-Uncensored-GGUF, is trending on Hugging Face. It is a vision-language model (image-text-to-text) with MoE architecture, formatted in GGUF for llama.cpp compatibility, and has had safety restrictions removed.
Related event: Uncensored Qwen3.8-Flash-Next Weights and GGUF Released(2 posts)→
More from Models
- GLM-5.3 Beats Flash on Accuracy but Costs 16x More in Benchmark — zainhas · 2026-08-29
- Minimax H3 demo mimics voice actors arguing in character — py-net · 2026-08-29
- Together AI: cascading GLM-5.3 Flash to GLM-5.3 cuts cost 57% while boosting DeepSWE to 80.9% — togethercompute · 2026-08-29
- LMMs fail to get the punchline of dinosaur extinction meme — NoYouDidLaugh · 2026-08-29
- Minimax H3 generates eulogy in Optimus Prime voice actor's style — Certain_Potato_4509 · 2026-08-29
- Cursor CEO: OpenAI models serve only 5% of user traffic — JP_525 · 2026-08-29