← Interactive LLM VRAM Calculator — try your own context length & quantization
How much VRAM to run Mistral 7B? (FP16/Q8/Q6/Q4 requirements)
Architecture: 32 layers, GQA with 8 KV heads. Figures are approximations for weights + an 8k-token FP16 KV cache + ~1 GB runtime overhead, based on typical published GGUF sizes. Actual usage varies by runtime and settings.
| Quantization | Weights | Total VRAM (8k context) | Fits on (example) |
|---|---|---|---|
| FP16 full precision (16-bit) | ~15 GB | ~17 GB | RTX 3090 / RTX 4090 (24 GB) |
| Q8_0 8-bit | ~7.7 GB | ~9.8 GB | RTX 3060 12 GB |
| Q6_K ~6.6-bit | ~5.9 GB | ~8.0 GB | RTX 3060 12 GB |
| Q5_K_M ~5.7-bit | ~5.1 GB | ~7.2 GB | RTX 3060 Ti / RX 7600 (8 GB) |
| Q4_K_M ~4.8-bit | ~4.4 GB | ~6.5 GB | RTX 3060 Ti / RX 7600 (8 GB) |
How much VRAM do I need to run Mistral 7B?
You need roughly ~6.5 GB of VRAM to run Mistral 7B at Q4_K_M with an 8k-token context — that fits on RTX 3060 Ti / RX 7600 (8 GB). At Q8_0 plan for about ~9.8 GB, and full FP16 needs around ~17 GB. Mistral 7B runs on almost anything: Q4_K_M needs well under 8 GB, and even FP16 fits on a 24 GB card. It remains a solid low-VRAM baseline model.
What affects these numbers?
Three things: the quantization (bytes per parameter), the KV cache (grows linearly with context length — the table assumes 8k tokens), and runtime overhead. Longer contexts need more memory; quantizing the KV cache (e.g. q8_0 cache in llama.cpp) roughly halves that part. Use the interactive calculator to plug in your exact context length and quantization.