models
Open weights, fine-tunes and adapters. Every listing here comes live from the Hugging Face Hub, attributed to it, and links back to the source.
Qwen3.5-397B-A17B-MXFP4-AttnFP8-V2Florence-2-large-no-flash-attnqwen3.8-27b-aeon-ultimate-uncensored-attention8-bf16recurrence-vision-mtplxornith-1.5-9b-attention8-bf16recurrence-vision-mlxMiniMax-M3-MXFP4-AttnFP8ornith-1.5-35b-a3b-abliterated-attention8-bf16recurrence-vision-mtplxqwopus3.8-27b-flash-abliterated-attention8-bf16recurrence-vision-mtplxornith-1.5-35b-a3b-attention8-bf16recurrence-vision-mtplxornith-1.5-9b-abliterated-attention8-bf16recurrence-vision-mtplxKimi-K3-Quark-MXFP4-AttnFP8Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-NEO-CODE-Di-IMatrix-MAX-GGUFTurkish-LLaVA-v0.1-Q4_K_M-GGUFCyber-Tiel-Coder-35B-A3B-MLX-Attention8-BF16Recurrence-MTPqwopus3.8-27b-flash-attention8-bf16recurrence-vision-mtplxGLM-5.3-Flash-NVFP4-attn-lmhead-W4A16AttilaAIQwen3.8-27B-W4A16-atlas-tunedmedix-qwen3.5-2b-vqa-attention-ffnmedix-qwen3.5-2b-vqa-attentionmedix-qwen3.5-2b-case-attention-ffnteaching-an-agent-to-sketch-one-part-at-a-timeGEMMA-AttackTree-DPOLFM2-VL-450M-r32-a32-lr2e-4-d0.05-tm-attentionmedix-qwen3.5-2b-knowledge-attentionmedix-qwen3.5-2b-knowledge-attention-ffnmedix-qwen3.5-2b-context-attention-ffnGEMMA-AttackTree-DPO_Augmentedvit-base-patch16-224-turkish-gpt2-mediumqwopus3.8-27b-flash-v2-attention8-bf16recurrence-vision-mtplxvit-small-patch16-224-turkish-small-bert-uncased
