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.
Qwen3-30B-A3B.w8a8Meta-Llama-3.1-8B-Instruct-quantized.w8a8Meta-Llama-3.1-8B-quantized.w8a8Qwen3-30B-A3B-Instruct-2507-quantized.w8a8tinyllama-oneshot-w8a8-channel-dynamic-token-v2tinyllama-oneshot-w8a8-dynamic-token-v2Qwen3-8B.w8a8tiny-qwen3-moe-w8a8-int8Qwen3-Coder-30B-A3B-Instruct-W8A8granite-4.1-3b-quantized.w8a8Mixtral-8x7B-Instruct-v0.1-w8a8-llmcompressor-v0.10.0.2Qwen3-4B-Instruct-2507-quantized.w8a8Meta-Llama-3.1-70B-Instruct-quantized.w8a8Qwen3.6-35B-A3B-w8a8-llmcompressorgpt-oss-20b-BF16-w8a8-llmcompressorInstella-MoE-16B-A3B-SFT-w8a8-llmcompressorMeta-Llama-3-8B-Instruct-quantized.w8a8Qwen3.8-27B-W8A8-INT8gemma-3-1b-it-quantized.w8a8Muse-Glimmer-30B-w8a8-llmcompressorQwen3.8-27B-w8a8-llmcompressorQwen3-4B.w8a8Qwen2-1.5B-Instruct-quantized.w8a8Qwen3-1.7B.w8a8DeepSeek-R1-Distill-Qwen-32B-quantized.w8a8DeepSeek-R1-Distill-Llama-70B-quantized.w8a8Phi-4-reasoning-plus-w8a8-llmcompressorgemma-4-26B-A4B-it-w8a8-llmcompressorQwen3-30B-A3B-Thinking-2507-quantized.w8a8gemma-4-12B-it-w8a8-llmcompressor