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-A0.9BGLM-5.2-0.8B-A0.8BQwen3.8-1.0B-A0.6BNemotronH-0.3B-A0.3BGLM-5.3-Flash-0.1B-A0.1BQwen3.8-Flash-Next-0.2B-A0.2BGLM-5.3-0.6B-A0.4BPhi-3.5-MoE-0.8B-A0.2BInkling-0.6B-A0.6BQwen3-VL-1.0B-A0.4B-InstructLlama-4-Scout-1.7B-0.4B-InstructDeepSeek-V4-Pro-0.5B-A0.37BQwen3.6-8B-A1.6BKimi-K3-0.40BQwen3-30B-A3B-Thinking-2507-REAP-25-uniformZAYA1-74B-preview-NVFP4Nemotron-3.5-Lightning-1.4B-A0.1B-MTPQwen3-30B-A3B-Thinking-2507-REAP-25-nonuniformQwen3-235B-A22B-Thinking-2507-quantized.w4a16DeepSeek-R1-Distill-Llama-8B-NVFP4GLM-5.2-0.8B-A0.8B-MXFP4xFP8_BLOCKGLM-5.2-0.8B-A0.8B-MXFP4xMXFP8Qwen3-235B-A22B-Thinking-2507-quantized.w8a8MiniMax-M2.5-BF16Qwen3-235B-A22B-Instruct-2507-quantized.w4a16Qwen3.6-35B-A3B-6.0-bits-mode-hybridQwen3.5-397B-A17B-FP8-dynamic-mtp-headDeepSeek-V3-0.86B-MTPDeepSeek-V3-0.86B-MTP-FP8-Dynamic
