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-4bitMinistral-3-8B-Reasoning-2512-AWQ-4bitLFM2.5-1.2B-Instruct-MLX-4bitLFM2-24B-A2B-MLX-4bitGLM-OCR-4bitNVIDIA-Nemotron-3-Nano-30B-A3B-MLX-4bitLlama-3.2-1B-Instruct-4bitMagistral-Small-2509-MLX-4bitMistral-Small-3.2-24B-Instruct-2506-MLX-4bitMinistral-3-14B-Instruct-2512-AWQ-4bitMinistral-3-3B-Instruct-2512-4bitLlama-3.2-3B-Instruct-4bitDevstral-Small-2507-MLX-4bitDevstral-Small-2505-MLX-4bitMeta-Llama-3.1-8B-Instruct-4bitMistral-Nemo-Instruct-2407-4bitLlama-3.3-70B-Instruct-4bitLFM2.5-1.2B-Instruct-4bitQwen3-ASR-0.6B-MLX-4bitQwen3-ForcedAligner-0.6B-4bitMinistral-3-3B-Instruct-2512-unsloth-bnb-4bitDevstral-Small-2507-AWQ-4bitNVIDIA-Nemotron-3.5-Lightning-30B-A3B-4bitMLX-Qwen3.5-9B-DeepSeek-V4-Flash-4bitLFM2.5-8B-A1B-MLX-4bitMinistral-3-14B-Instruct-2512-bnb-4bitLFM2.5-2.6B-4bitMinistral-3-8B-Instruct-2512-4bitSmolLM3-3B-4bitLFM2.5-VL-1.6B-4bit