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.
SmolLM-1.7B-Instruct-quantized.w4a16vietnamese-gpt2llama2.c-stories15MMeta-Llama-3-8B-Instruct-nonuniform-testtinyllama-oneshot-w4a16-channel-v2tinyllama-oneshot-w8w8-test-static-shape-changetinyllama-oneshot-w4a16-group128-v2Meta-Llama-3-8B-FP8-compressed-tensors-testconvert_modelopt_nvfp4-e2etinyllama-oneshot-w8a8-channel-dynamic-token-v2tinyllama-oneshot-w8a8-dynamic-token-v2tinyllama-oneshot-w8-channel-a8-tensortinyllama-oneshot-w8a16-per-channelQwen3-30B-A3B-FP8-blockQwen2-1.5B-Instruct-FP8W8Meta-Llama-3-70B-Instruct-FBGEMM-nonuniformconvert_awq_w4a16_asym-e2eTinyLlama-1.1B-compressed-tensors-kv-cache-schemeDeepSeek-R1-Distill-Qwen-32B-NVFP4llama7b-one-shot-2_4-w4a16-marlin24-tEpistemeAI.Reasoning-Llama-3.1-CoT-RE1-NMT-V3-ORPO-GGUFtinyllama-oneshot-w8a8-dynamic-token-v2-asymtinyllama-oneshot-w8a8-static-v2Meta-Llama-3-8B-Instruct-W4A16-compressed-tensors-testSmolLM-135M-Instruct-quantized.w4a16llama3-8b-w8_channel-a8_tensor-compressedDeepSeek-Coder-V2-Lite-Instruct-FP8tinyllama-one-shot-w4a16-group-packedMeta-Llama-3-8B-Instruct-W8A8-Dyn-Per-Token-2048-SamplesMeta-Llama-3.1-8B-Instruct-FP8-hf