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.
MiniMax-M3-MXFP4Qwen3.8-27B-Quark-AWQ-INT4-W4A16Qwen3.8-27B-Quark-AWQ-MXFP4Qwen3.5-397B-A17B-MXFP4Qwen3-VL-8B-Instruct-w8a8-llmcompressorQwen3-VL-235B-A22B-Instruct-MXFP4Qwen3.5-397B-A17B-MXFP4-AttnFP8-V2Qwen3.5-397B-A17B-NVFP4gemma-4-12B-it-w4a16-llmcompressorQwen3.8-Flash-Next-Quark-MXFP4Qwen3.5-35B-A3B-MXFP4Qwen3.6-35B-A3B-w4a16-llmcompressorgemma-4-26B-A4B-it-w4a16-llmcompressorQwen3.5-9B-w4a16-asym-torchao-v0.17.0Qwen3.8-27B-Quark-Qronos-INT4-W4A16Qwen3.8-Flash-Next-Quark-MXFP4-PLEFP8Swift-Qwen3.8-27b-int4-AMDMiniMax-M3-MXFP4-AttnFP8Qwen3-VL-8B-Instruct-w4a16-asym-torchao-v0.17.0Qwen3.6-35B-A3B-w8a8-llmcompressorMuse-Glimmer-30B-w8a8-llmcompressorQwen3.8-27B-w8a8-llmcompressorgemma-4-31B-it-MXFP4Qwen3.5-397B-A17B-MoE-MXFP4gemma-4-26B-A4B-it-w8a8-llmcompressorKimi-K3-Quark-MXFP4-AttnFP8gemma-4-12B-it-w8a8-llmcompressorSwift-Qwen3.8-27b-BF16-AMDQwen3-VL-8B-Instruct-w4a16-llmcompressorQwen3.6-35B-A3B-MXFP4-MOE-RTN
