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-Flash-Next-Uncensored-ROCmFP4-STRIX_LEAN-GGUFQwen3.8-27B-Atlassian-Q8-mlxQwen3.8-Flash-Next-ROCMFP4_STRIX_LEAN-GGUFDeepSeek-V4-Flash-180B-ROCmFP4-STRIX_LEAN-GGUFlean-finderQwen3.5-9B-Atlassian-Q8-mlxQwen3.8-27B-Atlassian-Q4-mlxQwen3.8-27B-Atlassian-Q6-mlxQwen3.8-Flash-Next-ROCmFP4-STRIX_LEAN-GGUFQwen3.5-9B-Atlassian-Q4-mlxQwen3.8-Flash-Next-Uncensored-ROCmFP4-STRIX_LEAN-imatrix-GGUFCHADROCK3.6-35B-UNCENSORED-MTP-STRIX-LEANQwen3.5-9B-Atlassian-Q6-mlxBonsai-REDUX2-GGUF-Q4_K_M-BLANK-PRIMED-V5-LeanV2-ggufQwen3.8-27B-MTP-Q4_0_ROCMFP4_STRIX_LEANQwen3.8-27B-lean-4bit-mlxSpark-X2.5-4B-ROCmFP4-STRIX_LEAN-GGUFQwen3.6-35B-A3B-ROCmFP4-STRIX_LEAN-DFLASH-GGUFBonsai-REDUX2-GGUF-Q4_K_M-Johnny-LORA-V4-LeanFix-ggufqwen3.8-4b-a1-omnimerge-m8qwen3.8-4b-a1-dare-tiesQwen3.8-27B-Atlassian-Q8-base-mlxlean-parrotQwen3.8-27B-Atlassian-lora-peftTiel-Coder-35B-A3B-ROCmFP4-STRIX_LEAN-GGUFQwen3.5-9B-Atlassian-Q8-base-mlxqwen3-4b-lean-compiler-v2NVIDIA-Nemotron-3.5-Lightning-30B-A3B-ROCmFP4-STRIX_LEANornith-1.0-9b-kubeops-GGUFLaguna-S-2.1-ROCmFP4-STRIX_LEAN-GGUF