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.
GLM-5.3-Int4-Int8Mix-RTN-g64Qwen3-30B-A3B-NVFP4-RTNGLM-5.3-Flash-W4A16-RTN-AutoRoundQwen3.5-4B-QuantStudy-RTN-W4A16SmolLM2-135M-QFS-rtn-int4-g64qwen2-0.5b-instruct-rtn-w8a16Qwen3.8-2.4T-A95B-W4A16-RTN-CT-AutoRoundQwen3-8B-FPQuant-RTN-MXFP4Qwen3-0.6B-FPQuant-RTN-MXFP4Qwen3-4B-FPQuant-RTN-MXFP4Llama-3.1-8B-Instruct-LC-SmoothQuant-RTN-W4A16Qwen3-0.6B-FPQuant-RTN-NVFP4Qwen3-4B-FPQuant-RTN-NVFP4Qwen3-1.7B-FPQuant-RTN-MXFP4Qwen3-8B-FPQuant-RTN-NVFP4Llama-3.1-8B-Instruct-LC-RTN-W4A16Meta-Llama-3.1-70B-Instruct-LC-RTN-W8A16Qwen3-1.7B-FPQuant-RTN-NVFP4Meta-Llama-3.1-70B-Instruct-LC-RTN-W4A16Meta-Llama-3.1-70B-Instruct-LC-RTN-W8A8Meta-Llama-3.1-70B-Instruct-LC-SmoothQuant-RTN-W4A16LGAI-EXAONE-4.0-32B-autoround-rtn-g128Phi-3-mini-4k-instruct-onnx-cpu-int4-rtn-block-32Llama-3.1-8B-Instruct-LC-SmoothQuant-RTN-W8A16Llama-3.1-8B-Instruct-LC-RTN-W8A8Llama-3.1-8B-Instruct-LC-RTN-W8A16Llama-3.1-8B-Instruct-LC-SmoothQuant-RTN-W8A8Meta-Llama-3.1-70B-Instruct-LC-SmoothQuant-RTN-W8A8Meta-Llama-3.1-70B-Instruct-LC-SmoothQuant-RTN-W8A16Phi-3-mini-128k-instruct-onnx-cpu-int4-rtn-block-32
