全站搜索
AI 模型 84762
- GLM-5.3-MLX-4bit↗
pipenetwork
- LFM3-Omni-2B-Pollard↗
PollardWeights
- Qwen-35B-A3B-SignOfFour-Coder-GGUF↗
pragmaticcs
> 🚀 **New Release:** Looking for my latest work? Check out the new **MiMo-HERO-Frontier-Agentic-Coder-9B-GGUF**! > Instant access is available to Pro members of my **Patreon community**. A four-way MoE merge of the Qwen 35B-A3B architecture, fusing task vectors from three specialized fine-tunes into a base anchor via DARE-TIES with sinusoidal depth modulation. > [!IMPORTANT] > Designed specifically to consolidate software engineering, code synthesis, and agentic tool execution capabilities. Multimodal vision weights and Multi-Token Prediction (MTP) heads were stripped to reduce VRAM footprint and maximize throughput during coding tasks.
- Llama-3.1-Korean-8B-Instruct-GGUF↗
QuantFactory
- OpenCodeReasoning-Nemotron-1.1-32B-GGUF↗
quantized4all
- OpenPhenom↗
recursionpharma
- microsoft_-_Phi-3-mini-128k-instruct-gguf↗
RichardErkhov
- PatronusAI_-_Llama-3-Patronus-Lynx-70B-Instruct-gguf↗
RichardErkhov
- Z-Image-Loras↗
SDim1973
+ Always use full LoRa name with "vrtlxxxx" trigger in prompt like "Alba Baptista (vrtlalbabaptista) in a swimming pool". "Woman" or "1girl" will NOT work due to my way i do captions. + Remove the name when internal model knowledge is bad or censored or is confusing to model like "Sandy Cheeks" or "Kate Middleton". + When using a Lora with multiple triggers (vrtlxx,vrtlyy) do not use the real character name but only trigger or a combination of it. "vrtlMain" always combines all trigger-words.
- nltower-100m-sft-tw1X-e4↗
sfanm
