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.
gemma4-cpu-moe-ggufPhi-3-medium-4k-instruct-onnx-cpuPhi-3-medium-128k-instruct-onnx-cpuMiniCPM5-2B-cpudeepseek-moe-16b-q4-k-m-cpu-offload-ggufPhi-3-vision-128k-instruct-onnx-cpuCotype-Nano-CPUgpt-oss-20b-moe-cpu-offload-ggufAstrid-1B-CPULLaMa3-xdfg-cpudeepseek-moe-16b-q8-0-cpu-offload-ggufMamba_Hermes-3B-GPU-CPU-v0.2-GGUFDeepSeek-V3-0324-GPU-FP8-GPTQ4gpt-neo-2.7B__low-cpuEdge4-SQL-CPU-Q4_K_Mmamba-bagel-2.8b-GPU-CPU-v0.2-GGUFdeepseek-moe-16b-cpu-offload-ggufmpt-7b-storywriter-4bit-128g-65kTokens-CPUDeepSeek-V3.2-CPU-NUMA4-AMXINT8phi-3.5-moe-cpu-offload-ggufdeepseek-moe-16b-q2-k-cpu-offload-ggufDeepSeek-V3-0324-CPU-NUMA4-AMXINT4DeepSeek-V3-0324-CPU-NUMA4-AMXINT8modello-italia-9b-autoround-w4g128-cputiny-random-LlamaForCausalLM-cpuDeepSeek-R1-0528-GPU-FP8-GPTQ4medical-deepseek-merged-cpuLlama-3.2-1B-cputrained-robincnpdeepseek-customer-bot-cpu-finetunedcpu-optimized-medical-model
