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.
NVIDIA-Nemotron-3-Nano-Omni-30B-A3B-Reasoning-GGUFQwen3.5-397B-A17B-Opus-4.6-Reasoning-Uncensored-GGUFLlama3.3-8B-Instruct-Thinking-Heretic-Uncensored-Claude-4.5-Opus-High-Reasoning-mlx-8Bitcommand-a-reasoning-08-2025Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning-GGUFLlama3.1-MOE-4X8B-Gated-IQ-Multi-Tier-Deep-Reasoning-32B-GGUFLlama3.1-MOE-4X8B-Gated-IQ-Multi-Tier-COGITO-Deep-Reasoning-32B-GGUFQwen3.5-122B-A10B-Opus-Reasoning-GGUFLlama3.3-8B-Instruct-Thinking-Heretic-Uncensored-Claude-4.5-Opus-High-ReasoningNVIDIA-Nemotron-Labs-Teacher-General-ReasoningDavidAU__Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning-mlx-mxfp4Qwen3.5-397B-A17B-Opus-4.6-Reasoning-Uncensored-GGUFQwen3.5-397B-A17B-Opus-4.6-Reasoning-Uncensored-GGUFNVIDIA-Nemotron-3-Nano-Omni-30B-A3B-ReasoningLlama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-ReasoningLlama3.3-8B-Instruct-Thinking-Heretic-Uncensored-Claude-4.5-Opus-High-Reasoning-mlx-2BitLlama3.3-8B-Instruct-Thinking-Heretic-Uncensored-Claude-4.5-Opus-High-Reasoning-mlx-8BitNVIDIA-Nemotron-3-Nano-Omni-30B-A3B-Reasoning-GGUFLlama3.3-8B-Instruct-Thinking-Heretic-Uncensored-Claude-4.5-Opus-High-Reasoning-IQ4_NL-GGUFQwen3.5-122B-A10B-Opus-Reasoning-GGUFLlama3.3-8B-Instruct-Thinking-Heretic-Uncensored-Claude-4.5-Opus-High-Reasoning-Q8_0-GGUFoellm-9b-256k-reasoning-v1Llama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning-Q4_K_M-GGUFNVIDIA-Nemotron-3-Nano-Omni-30B-A3B-Reasoning-GGUFMistral-Nemo-Instruct-2407-12B-Thinking-HI-Claude-Opus-High-Reasoning-mxfp4-mlxLlama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning-Q6_K-GGUFMistral-Nemo-Instruct-2407-12B-Thinking-M-Claude-Opus-High-ReasoningLlama3.1-MOE-4X8B-Gated-IQ-Multi-Tier-Deep-Reasoning-32BGemma-3-27b-it-HERETIC-Gemini-Deep-Reasoning-q8-mlxQwen3.5-397B-A17B-Opus-4.6-Reasoning