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.
Qwen-3.8-27B-ROCmFP4-FAST-GGUFQwen3.8-Flash-Next-ROCMFP4_STRIX_LEAN-GGUFQwen3.8-27B-ROCmFPX-Q8_0-AGENT-GGUFQwen3.8-27B-PaoAI-ROCmFP4-STRIX-BALANCED-GGUFDeepSeek-V4-Flash-0731-ROCmFP4MN-Rocinante-18.5B-v1.1-Story-Wizard-ED1-Instruct-GGUFQwen3.8-27B-MTP-Q4_0_ROCMFP4_STRIX_LEANQwen3.8-Flash-Next-MLX-4bitQwen3.8-27B-ROCmFPX-GGUFNVIDIA-Nemotron-3.5-Lightning-30B-A3B-ROCmFP4-STRIX_LEANQwen3.8-27B-ROCmFPX-Q8_0-GGUFLaguna-S-2.1-Chadrock-ROCmFP4-StrixKVSpine-V4-GGUFQwopus3.6-27B-Coder-MTP-ROCmFPXQwopus3.6-27B-v2-MTP-ROCmFPXZAYA1-8B-ROCmFP4-GGUFNVIDIA-Nemotron-3.5-Lightning-30B-A3B-ROCmFP4-GGUFneotoi-coder-4bTess-4-27B-ROCmFPX-GGUFLlama3.2-24B-A3B-II-Dark-Champion-INSTRUCT-Heretic-Abliterated-Uncensored-ROCMFP4_FASTQwen3.8-27B-MTP-Q3_0_ROCMFPXQwen3.6-27B-Fable-Fusion-711-MTP-ROCmFPX-GGUFPhoneLLM-Alpha-1-ROCmFP4-GGUFRocketGuard-1b-GGUFqwable-5-27b-chadrock-v2-rocmfp4Mellum2-12B-A2.5B-Thinking-ROCmFP4-GGUFMellum2-12B-A2.5B-Instruct-ROCmFP4-GGUFGigaChat3.1-10B-A1.8B-MLX-4bitLing-3.0-tiny-ROCmFP4-GGUFLFM2-24B-A2B-ROCmFPX-GGUFQwen3.6-35B-A3B-ROCMFP