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-ROCMFP4_STRIX_LEAN-GGUFQwen3.8-27B-Atlassian-Q8-mlxQwen3.5-9B-Atlassian-Q8-mlxQwen3.8-27B-MTP-Q4_0_ROCMFP4_STRIX_LEANQwen3.8-27B-Atlassian-Q6-mlxQwen3.8-27B-Atlassian-Q4-mlxQwen3.5-9B-Atlassian-Q4-mlxQwen3.5-9B-Atlassian-Q6-mlxNVIDIA-Nemotron-3.5-Lightning-30B-A3B-ROCmFP4-STRIX_LEANCHADROCK3.6-35B-UNCENSORED-MTP-STRIX-LEANQwen3.8-27B-Atlassian-Q8-base-mlxQwen3.5-9B-Atlassian-Q8-base-mlxPhoneLLM-Alpha-1-ROCmFP4-STRIX-LEAN-GGUFQwen3.8-27B-Atlassian-Q8_0-GGUFQwen3.8-27B-Atlassian-Q6_K-GGUFLeanstral-1.5-119B-A6B-ROCmFP4-STRIX_LEAN-GGUFQwen3.8-27B-Atlassian-lora-peftCHADROCK3.6-35B-UNCENSORED-MTP-STRIX-LEANNemotron-3-Nano-30B-A3B-ROCmFP4-STRIX_LEAN-GGUFCode-Writer-V2-Obliterated-AWQ-Mixed-Leanllama3-8b-leandojo-informalizedleannelleeds-scalziyung-leanqwen2.5-coder-1.5b-lean-repository-midtrainingSTP_model_Lean_0320-conjecture-base-FineTune-new-configSTP_model_Lean_0320-conjecture-base-FineTune-new-config-conjecture-base-FineTune-new-config-v2DeepSeek-R1-Distill-Qwen-32B-for-leanQwen3.8-27B-Atlassian-loraQwen3.5-9B-Atlassian-loraqwen3.8-4b-a1-dare-ties