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-4bitLFM2.5-1.2B-Instruct-MLX-4bitLFM2-24B-A2B-MLX-4bitNVIDIA-Nemotron-3-Nano-30B-A3B-MLX-4bitLlama-3.2-1B-Instruct-4bitLlama-3.2-3B-Instruct-4bitDevstral-Small-2505-MLX-4bitMeta-Llama-3.1-8B-Instruct-4bitLlama-3.3-70B-Instruct-4bitLFM2.5-1.2B-Instruct-4bitMLX-Qwen3.5-9B-DeepSeek-V4-Flash-4bitNVIDIA-Nemotron-3.5-Lightning-30B-A3B-4bitLFM2.5-8B-A1B-MLX-4bitSmolLM3-3B-4bitLFM2.5-2.6B-4bitLFM2.5-1.2B-Instruct-MLX-4bitgranite-4.2-8b-MLX-4bitLFM2.5-2.6B-MLX-4bitLFM2.5-230M-MLX-4bitMeta-Llama-3.1-70B-Instruct-4bitLFM2.5-8B-A1B-MLX-4bitgranite-4.2-30b-MLX-4bitLFM2.5-2.6B-MLX-4bitgranite-4.2-3b-MLX-4bitNVIDIA-Nemotron-Nano-9B-v2-AWQ-4bitMamba-Codestral-7B-v0.1-instruct-python_coding_assistant-GGUF_4bitEuroLLM-1.7B-Instruct-mlx-4BitLFM2.5-350M-MLX-4bitMistral-Small-3.2-24B-Instruct-2506-4bitLFM2-1.2B-unsloth-bnb-4bit