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.
DeepSeek-R1-MXFP4MiniMax-M3-MXFP4amd.Instella-MoE-16B-A3B-Think-GGUFKimi-K2.5-MXFP4GLM-5.2-MXFP4Qwen3.8-27B-Quark-AWQ-MXFP4Qwen3.8-27B-Quark-AWQ-INT4-W4A16wav2vec2-base-finetuned-amdQwen3.8-2.4T-A95B-Quark-MXFP4GLM-5.3-Flash-Quark-MXFP4Llama-3.3-70B-Instruct-FP8-KVQwen3.5-397B-A17B-MXFP4GLM-5.3-Quark-MXFP4-AttnFP8Qwen3.5-397B-A17B-MXFP4-AttnFP8-V2Qwen3.8-Flash-Next-Quark-MXFP4gpt-oss-120b-w-mxfp4-a-fp8grok-1-W4A8KV8AMD-Llama-135mQwen3-VL-235B-A22B-Instruct-MXFP4DeepSeek-R1-0528-MXFP4Kimi-K2.6-MXFP4DeepSeek-R1-0528-MXFP4-MTP-MoEFP4DeepSeek-V4-Flash-MXFP4gpt-oss-20b-WFP8-AFP8-KVFP8gpt-oss-20b-MoE-Quant-W-MXFP4-A-FP8-KV-FP8tiny-random-qwen3_moeAMD-OLMo-1B-SFT-DPO-GGUFLlama-3.1-8B-Instruct-FP8-KVInstella-MoE-16B-A3B-Thinkgemma-4-26B-A4B-it-w4a16-llmcompressor
