サイト内検索

AI モデル 84760

• noob-ipa↗

  subby2006

• d1-3B-GGUF↗

  TechnoBaptist

• LlongOrca-13B-16K-GGUF↗

  TheBloke

• Hemispheres-v0.2-Llama3.2-3B-Final↗

  theprint

• pit_ti_224.in1k↗

  timm

• vit_srelpos_small_patch16_224.sw_in1k↗

  timm

• dots.llm1.inst-GGUF↗

  unsloth

• gemma-3-4b-it-qat-int4-GGUF↗

  unsloth

• Kimi-K2-Instruct-GGUF↗

  unsloth

  It is recommended to have at least 128GB unified RAM memory to run the small quants. With 16GB VRAM and 256 RAM, expect 5+ tokens/sec. For best results, use any 2-bit XL quant or above. 📰   Tech Blog     |     📄  Paper Link (coming soon) Kimi K2 is a state-of-the-art mixture-of-experts (MoE) language model with 32 billion activated parameters and 1 trillion total parameters. Trained with the Muon optimizer, Kimi K2 achieves exceptional performance across frontier knowledge, reasoning, and coding tasks while being meticulously optimized for agentic capabilities.

• Mistral-Small-24B-Instruct-2501-bnb-4bit↗

  unsloth