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.
Qwen2.5-VL-3B-Instruct-quantized.w8a8Qwen3-VL-8B-Instruct-w8a8-llmcompressorQwen2.5-VL-7B-Instruct-quantized.w8a8Qwen3.8-27B-INT8-W8A8Qwen3.5-4B-quantized.w8a8Qwen3.5-9B-quantized.w8a8NuExtract3-W8A8Mistral-Small-3.1-24B-Instruct-2503-quantized.w8a8Qwen3.8-27B-INT8-W8A8-imatrix-MTPgemma-3-4b-it-quantized.w8a8Qwen3.8-27B-heretic-SmoothQuant-W8A8-INT8Gemma-4-31B-it-Quark-W8A8-INT8Qwen3.6-35B-A3B-w8a8-llmcompressorQwen3.6-35B-A3B-Quark-W8A8-INT8Qwen3.8-27B-GPTQ-INT8-W8A8-GS128Gemma-4-31B-it-uncensored-heretic-Quark-W8A8-INT8Qwen3-VL-Embedding-8B-W8A8Ornith-1.5-35B-A3B-abliterated-W8A8Muse-Glimmer-30B-w8a8-llmcompressorQwen3.8-27B-w8a8-llmcompressorgemma-3-27b-it-quantized.w8a8Swift-Qwen3.8-27b-heretic-W8A8-DFlash2gemma-3-12b-it-quantized.w8a8gemma-4-26B-A4B-it-w8a8-llmcompressorMuse-Glimmer-30B-W8A8-INT8Muse-Glimmer-30B-SOMPOA-heresy-W8A8gemma-4-12B-it-w8a8-llmcompressorQwen3.6-27B-Quark-W8A8-INT8Qwen3.8-27B-GPTQ-INT8-W8A8-GS128-PTQRQwen2.5-VL-72B-Instruct-quantized.w8a8
