Local LLM memory requirements

Explore estimated GPU VRAM and system RAM for each model. Compare supported weight formats at an 8K context, or the model's lower native limit. These are planning estimates for one conversation with full GPU offload.

Looking for ChatGPT, Claude, Gemini or Codex? Read our local vs hosted AI guide.

• DeepSeek R1 Distill Qwen 1.5B VRAM and RAM requirements · DeepSeek
• DeepSeek R1 Distill Qwen 7B VRAM and RAM requirements · DeepSeek
• DeepSeek R1 Distill Qwen 14B VRAM and RAM requirements · DeepSeek
• DeepSeek R1 Distill Qwen 32B VRAM and RAM requirements · DeepSeek
• Gemma 3 1B Instruct VRAM and RAM requirements · Google
• Gemma 3 4B Instruct VRAM and RAM requirements · Google
• Gemma 3 12B Instruct VRAM and RAM requirements · Google
• Gemma 3 27B Instruct VRAM and RAM requirements · Google
• gpt-oss 20B VRAM and RAM requirements · OpenAI
• gpt-oss 120B VRAM and RAM requirements · OpenAI
• Llama 3.1 8B VRAM and RAM requirements · Meta
• Llama 3.1 70B VRAM and RAM requirements · Meta
• Llama 3.1 405B VRAM and RAM requirements · Meta
• Qwen 2.5 0.5B Instruct VRAM and RAM requirements · Qwen
• Qwen 2.5 1.5B Instruct VRAM and RAM requirements · Qwen
• Qwen 2.5 7B Instruct VRAM and RAM requirements · Qwen
• Qwen 2.5 14B Instruct VRAM and RAM requirements · Qwen
• Qwen 2.5 32B Instruct VRAM and RAM requirements · Qwen
• Qwen3 0.6B VRAM and RAM requirements · Qwen
• Qwen3 1.7B VRAM and RAM requirements · Qwen
• Qwen3 4B VRAM and RAM requirements · Qwen
• Qwen3 8B VRAM and RAM requirements · Qwen
• Qwen3 14B VRAM and RAM requirements · Qwen
• Qwen3 32B VRAM and RAM requirements · Qwen
• Yi 1.5 6B Chat VRAM and RAM requirements · 01.AI
• Yi 1.5 9B Chat VRAM and RAM requirements · 01.AI

Longer context, concurrent users and runtime settings can increase memory use. Check the actual model download before buying hardware.