How much VRAM do you need for each local LLM?
Last updated:
One page per current model: weight math (Q4_K_M and other quants) plus the measured RigBase results. Leave room for the KV cache on top of the weights.
- How much VRAM for Qwen3.8 27B?
- How much VRAM for Gemma 4 31B?
- How much VRAM for gpt-oss 120B?
- How much VRAM for Qwen3.6 35B-A3B?
- How much VRAM for gpt-oss 20B?
- How much VRAM for Gemma 4 26B-A4B?
- How much VRAM for Qwen3.8 Flash-Next?
- How much VRAM for Nemotron 3.5 Bolt 74B-A9B?
- How much VRAM for DeepSeek V4.1 Flash?
- How much VRAM for Gemma 4 12B?
- How much VRAM for Qwen3.5 9B?
- How much VRAM for GLM-5.3 Flash?
- How much VRAM for MiniMax M3.1 Flash?
- How much VRAM for Muse Spark Open 816B-A42B?
- How much VRAM for Mistral Medium 3.5 128B?
- How much VRAM for Flint 40B-A2.5B?
- How much VRAM for Ornith 1.5 35B-A3B?
Also: best LLMs by VRAM size · VRAM calculator · all models