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.
Qwen3-4BNVIDIA-Nemotron-3-Nano-4B-BF16Qwen3-4B-Instruct-2507Qwen3-Reranker-4BQwen3-Embedding-4BGemma-4-26B-A4B-NVFP4Qwen3-4B-BaseOTel-LLM-E4B-ITLlama-3.1-8B-Instruct-4bitQwen3-4B-Instruct-2507-FP8Qwen3-Coder-30B-A3B-Instruct-AWQ-4bitQwen3.8-4B-Distill-GGUFQwen3-Reranker-4B-W4A16-G128Qwen3-4B-GGUFgemma4-e4b-claims-comparisonParable-Qwen3-4B-Claude-Fable-5-GGUFQwen3-Embedding-4B-W4A16-G128Qwen3-4B-GGUFQwen3-4B-Thinking-2507mistral-7b-v0.3-bnb-4bitSpark-X2.5-4B-GGUFAgents-A1-4BQwen2.5-14B-bnb-4bitDeepSeek-R1-0528-Qwen3-8B-MLX-4bitJan-v3.5-4B-ggufQwen3-4B-GGUFQwen2.5-Coder-7B-Instruct-4bitQwen3-4B-AWQqwen3-4b-base-dapo-v4Ornith-1.5-9B-MLX-4bit
