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.
Llama-3.2-0.5B-InstructQwen3-1.6B-A0.9BQwen3-8B-from-Qwen3-8B_regen-speculators.eagle3-qwen3arch-ckpt1Qwen3-8B-speculators.peagle-qwen3arch-ckpt4Qwen3-Coder-Next.w4a16GLM-5.2-0.8B-A0.8BDSV4-tiny-emptyDeepSeek-V3-debug-empty-FP8_DYNAMICQwen3.8-1.0B-A0.6BQwen3-8B-speculator.dspark.swa.dpace.fullvocab.muon.2048anc.combdatav4-q235b-instr-v1-ckpt2Qwen3-8B-speculator.dflash.swa.dpace.fullvocab.muon.2048anc.combdatav3-q235b-instr-v9-ckpt19Qwen3-8B-speculator.dflash.swa.dpace.fullvocab.muon.2048anc.combdatav3-q235b-instr-v9-ckpt16Kimi-K3-0.40B-MXFP4NemotronH-0.3B-A0.3Bqwe3-8B-selfdistill-v3-fresh3ep_ckpt0GLM-5.3-Flash-0.1B-A0.1BKimi-K3-0.40BQwen3-8B-speculator.dflash.swa.dpace.fullvocab.muon.2048anc.combdatav3-q235b-instr-v9-ckpt12DeepSeek-V3-debug-emptyQwen3.8-Flash-Next-0.2B-A0.2BNemotron-3.5-Lightning-1.4B-A0.1B-MTPLlama-3.2-1B-Instruct-FP8-Blocksarvam-30b-NVFP4gemma-4-1B-0.8B-tinyQwen3.6-8B-A1.6BQwen3-0.6B-W4A16-G128Qwen3-VL-Reranker-0.1B-tinyGLM-5.3-0.6B-A0.4BDeepSeek-V4-Pro-0.5B-A0.37BInkling-0.6B-A0.6B
