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.
Qwen3.8-2.4T-A95B-Quark-MXFP4GLM-5.3-Quark-MXFP4-AttnFP8Instella-MoE-16B-A3B-Thinkgemma-4-12B-it-w4a16-llmcompressorPhi-4-reasoning-plus-w4a16-llmcompressorInstella-MoE-16B-A3B-SFTMiniMax-M2.1-MXFP4gemma-4-26B-A4B-it-w4a16-llmcompressorQwen3.5-9B-w4a16-asym-torchao-v0.17.0Qwen3.6-35B-A3B-w4a16-llmcompressorMixtral-8x7B-Instruct-v0.1-w8a8-llmcompressor-v0.10.0.2Llama-3.1-8B-Instruct-w4a16-asym-torchao-v0.17.0Mixtral-8x7B-Instruct-v0.1-w4a16-llmcompressorQwen3-235B-A22B-Instruct-2507-MXFP4Phi-4-reasoning-plus-w4a16-asym-torchao-v0.17.0Qwen3.6-35B-A3B-w8a8-llmcompressorgpt-oss-20b-BF16-w8a8-llmcompressorMiniMax-M2.7-MXFP4Qwen3-Coder-480B-A35B-Instruct-MXFP4Instella-MoE-16B-A3B-BaseInstella-MoE-16B-A3B-SFT-w8a8-llmcompressorDeepSeek-V4-Pro-NVFP4Instella-MoE-16B-A3B-PretrainMuse-Glimmer-30B-w8a8-llmcompressorQwen3.8-27B-w8a8-llmcompressorQwen2.5-Coder-7B-Instruct-onnx-ryzenai-npuInstella-MoE-16B-A3B-DPOPhi-4-mini-instruct-w4a16-llmcompressorCyberSecQwen-4BInstella-MoE-16B-A3B-Midtrain