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-Coder-30B-A3B-Instruct-FP4Ling-3.0-flash-fp4Qwen3-30B-A3B-Instruct-2507-FP4Qwen3-30B-A3B-Thinking-2507-FP4Qwen3.8-27B-FP4MiMo-V2.5-Pro-FP4-DFlashdeepseek-v4-fp4-fp8-tiny-randomQwen3-0.6B-FP4Qwen2.5-14B-Instruct-FP4-W4A4DFM-Mimir-FP4-MLXQwen3.6-27B-Uncensored-Aquarion-FP4Qwen3-235B-A22B-Instruct-2507-FP4DeepSeek-V4-Flash-REAP128-FP4Ling-3.0-flash-Fin-fp4Qwen3-235B-A22B-Thinking-2507-FP4-Eagle3Qwen3-32B-FP4DeepSeek-V4-Flash-FP4-FP8-SSDQwen3-32B-fp4Qwen2.5-3B-Instruct-FP4-W4A4DeepSeek-V4-Flash-REAP152-FP4Qwen2.5-1.5B-Instruct-w4a4-fp4DeepSeek-V4-Pro-FP4PTPCc4ai-command-a-03-2025-4bit_fp4Qwen3-8B-fp4Qwen3.6-27B-Feral-Aquarion-FP4DFM-Mimir-AWQ-FP4Qwen3.6-35B-A3B-DSV4Pro-TextOnly-FP4MiMo-V2.5-Pro-FP4-DFlash-pruned-8expertsPhind-CodeLlama-34B-Python-v1_8bit_fp4Qwen3-Coder-480B-A35B-Instruct-FP4
