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-Reranker-4B-W4A16-G128Qwen3-Embedding-4B-W4A16-G128granite-3.1-2b-instruct-quantized.w4a16Meta-Llama-3.1-8B-Instruct-quantized.w4a16NVIDIA-Nemotron-3.5-Lightning-30B-A3B-W4A16DeepSeek-R1-Distill-Qwen-32B-quantized.w4a16Ornith-1.5-9B-INT4-W4A16-AutoRoundQwen3-0.6B-quantized.w4a16Qwen3-8B-quantized.w4a16Qwen3-32B-quantized.w4a16Meta-Llama-3.1-70B-Instruct-quantized.w4a16gemma-4-E4B-it-W4A16-AutoRound-GPTQQwen3-4B-quantized.w4a16octen-embedding-8b-w4a16tinyllama-oneshot-w4a16-channel-v2Qwen2.5-Omni-7B-W4A16GLM-5.3-Flash-W4A16-AutoRoundQwen3-30B-A3B-Instruct-2507-quantized.w4a16tinyllama-oneshot-w4a16-group128-v2gemma-4-12B-it-w4a16-llmcompressorQwopus3.8-27B-Flash-INT4-W4A16Qwen3-30B-A3B-quantized.w4a16Phi-4-reasoning-plus-w4a16-llmcompressorQwen3.6-35B-A3B-w4a16-llmcompressormeta-llama.Llama-3.2-3B-Instruct_W4A16gemma-4-26B-A4B-it-w4a16-llmcompressorQwen3.8-27B-heretic-ara-W4A16MiniMax-M2.7-REAP-172B-A10B-AutoRound-W4A16Phi-3-medium-128k-instruct-quantized.w4a16gemma-4-12B-it-W4A16-GPTQ-g32-DSpark