Search FoxAI

AI Models 84759

• codegemma-7b-pytorch↗

  Google

• Qwen3.8-Flash-Next-Heretic-GGUF↗

  groxaxo

• Holo4-35B-A3B-FP8↗

  Hcompany

• ncii-guard-v02↗

  hfmlsoc

  A binary classifier that flags image-editing prompts seeking non-consensual intimate imagery (NCII): requests to strip, undress, or otherwise sexualise a person in a photograph. It is `microsoft/harrier-oss-v1-270m` with a LoRA adapter (r=8) merged in, so it loads with plain `transformers` and needs no `peft`. The unmerged adapter is kept under `adapter/`. **This model does not ship a recommended threshold, and the default 0.5 is not a neutral choice.** Precision on clean text runs from 0.870 at 0.5 to 0.951 at 0.935, and buying that precision costs recall against obfuscated input: across 35 attack families the model misses 617 of 2,070 obfuscated NCII prompts at 0.5 and 749 at 0.935. Which way to err depends on what we need to prioritize. Pick the threshold against the precision/recall tradeoff. The full sweep for dev here is in `eval/`, both on clean text and per attack family.

• K2-Type-0.9B↗

  IFM

• Llama-Krikri-8B-Instruct-GGUF↗

  ilsp

• gemma-4-12B-it-qat-GGUF-UD-Q4_K_XL-layers↗

  ilya-chak

• Qwen3.6-35B-A3B-int4-mixed-AutoRound↗

  Intel

  This model is a mixed int4 model with group_size 128 of Qwen/Qwen3.6-35B-A3B generated by intel/auto-round. Please follow the license of the original model. **Some users have reported an infinite loop issue in our INT4 version. We have added fallbacks for certain layers in this release, but it is still unclear whether the issue has been fully resolved. Please use it with caution.** The main branch is generated by `auto-round-best` and revision 54e7cd36d9f7a358b4b42740c3aef755638e5ea6 is generated by `auto-round`. Tipically `auto-round-best` is better

• Qwen3.5-9B-Distill-Deepseek-V4.1-Flash-20261003↗

  kevinzhou21

  This model is a merged LoRA fine-tune of **Qwen3.5-9B**, mimicking the behavioral distribution of **DeepSeek-V4.1-Flash**. **Example usage**: - For text only LLMs: `llama-cli -hf kevinzhou21/Qwen3.5-9B-Distill-Deepseek-V4.1-Flash-20261003 --jinja` - For multimodal models: `llama-mtmd-cli -hf kevinzhou21/Qwen3.5-9B-Distill-Deepseek-V4.1-Flash-20261003 --jinja`

• Kimi-VL-A3B-Thinking-2506↗

  月之暗面 · Kimi

  > [!Note] > This is an improved version of Kimi-VL-A3B-Thinking. Please consider using this updated model instead of the previous version. > [!Note] > Please visit our tech blog for recommended inference recipe of this model: Kimi-VL-A3B-Thinking-2506: A Quick Navigation Comparison with efficient models and two previous versions of Kimi-VL (*Results of GPT-4o is for reference here, and shown in italics ):