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.
Llama-3.1-8B-Instruct-4bite5-mistral-7b-instruct-bnb-4bitmistral-7b-v0.3-bnb-4bitQwen2.5-Coder-7B-Instruct-4bitOrnith-1.5-9B-MLX-4bitOrnith-1.5-35B-A3B-MLX-4bitQwen3.6-27B-GPTQ-Pro-4bitQwen3-14B-unsloth-bnb-4bitQwen2.5-Coder-14B-Instruct-MLX-4bitall-MiniLM-L6-v2-4bitGLM-4.6V-Flash-MLX-4bitMinistral-3-8B-Reasoning-2512-AWQ-4bitQwen2.5-3B-Instruct-unsloth-bnb-4bitLFM2.5-1.2B-Instruct-MLX-4bitLFM2-24B-A2B-MLX-4bitMeta-Llama-3.1-8B-Instruct-bnb-4bitQwen2.5-Coder-7B-Instruct-bnb-4bitQwopus3.6-27B-v2-AWQ-4bitLlama-3.2-3B-Instruct-bnb-4bitGLM-OCR-4bitQwen3-4B-unsloth-bnb-4bitllama-3-8b-Instruct-bnb-4bitLlama-3.2-3B-Instruct-unsloth-bnb-4bitQwen2.5-1.5B-Instruct-bnb-4bitQwen3-1.7B-unsloth-bnb-4bitLlama-3.2-1B-Instruct-bnb-4bitQwen2.5-1.5B-Instruct-unsloth-bnb-4bitQwen2.5-Coder-32B-Instruct-MLX-4bitNVIDIA-Nemotron-3-Nano-30B-A3B-MLX-4bitPhi-4-mini-reasoning-MLX-4bit