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-moe-pre-v5-loraless-is-moe-qwen3.5-122b-a10b-gpqa-main-64-intdim-g-50less-is-moe-qwen3.5-122b-a10b-s1-128-seq8192-intdim-l-50less-is-moe-qwen3.5-122b-a10b-s1-128-seq8192-intdim-g-50less-is-moe-qwen3.5-122b-a10b-gpqa-main-64-intdim-l-50less-is-moe-qwen3.5-122b-a10b-gpqa-main-64-intdim-e-50less-is-moe-qwen3.5-122b-a10b-s1-128-seq8192-intdim-e-50Qwen3.6-35B-MoE-Q5Qwen3.5-35B-A3B-bitplanner-b4-5-moefloor-imatrix-scaleclip-routerw-exportrepQwen3-MOE-4x4B-16B-Jan-Polaris-Instruct-Power-House-Q5_K_M-GGUFqwen3_5_moe_35b_a3b_baseQwen3-235B-A22B-Instruct-2507-MXFP4_MOEqwen3_5_moe_35b_a3bmoe-200m-qwen3-step160000-5B-20260522-2256Qwen3-MOE-6x6B-Star-Trek-Universe-Alpha-D-256k-ctx-36B-Q5_K_M-GGUFqwen35-moe-v20-loraQwen3-30B-A3B-Base-SGLang-ModelOpt-NVFP4-MoEOnly-FusedSQ0p5-wikitext512-seq2048Qwen3-235B-A22B-Thinking-2507-MXFP4_MOEqwen3-vl-moe-tiny-lora-transformers5.xqwen35-moe-4bitpredictor_math-500_Qwen3-30B-A3B_moe_patterns_finetuneqwen35-moe-v20-checkpointqwen35moe-blackhole-p100-slim-gate-up-fused-2026-05-24Qwen3-4B-Thinking-2507-SDPOthink5-MathQwen3-4B-Thinking-2507-SDPO5-MathQwen3-4B-Thinking-2507-SDPO5-ChemQwen3-4B-Thinking-2507-SDPO5-ToolQwen3-30B-A3B-Base-Megatron-ModelOpt-NVFP4-MoEOnly-FusedSQ0p5-wikitext512-seq2048Qwen3-4B-Thinking-2507-SDPOthink5-ChemQwen3-4B-Thinking-2507-SDPOthink5-Tool