canirunthismodel

Can you run these AI models locally?

Pick a model to see its exact VRAM & RAM requirements, whether it runs on your GPU, and copy-paste commands for Ollama, llama.cpp and vLLM. Or paste any Hugging Face model to check one that isn't listed.

Popular models

Qwen2.5-0.5B0.5B · LLM GPT-2124M · LLM Phi-3-mini3.8B · LLM Qwen2.5-Coder7B · CODE Mistral-7B7B · LLM Llama-3.1-8B8B · LLM Gemma-2-9B9B · LLM Qwen2.5-14B14B · LLM Qwen2.5-32B32B · LLM Mixtral-8x7B47B · LLM Llama-3.1-70B70B · LLM DeepSeek-R1-7B7B · LLM SDXL3.5B · IMAGE FLUX.1-dev12B · IMAGE Whisper-large-v31.5B · AUDIO all-MiniLM-L622M · EMBED