← Interactive LLM VRAM Calculator — try your own context length & quantization
How much VRAM to run Mixtral 8x7B? (FP16/Q8/Q6/Q4 requirements)
Architecture: Mixture-of-Experts: 46.7B total / ~12.9B active parameters, 32 layers, 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) | ~93 GB | ~95 GB | 2×RTX A6000 (96 GB) |
| Q8_0 8-bit | ~50 GB | ~52 GB | 2×RTX 5090 (64 GB) |
| Q6_K ~6.6-bit | ~38 GB | ~40 GB | 2×RTX 3090 or RTX A6000 (48 GB) |
| Q5_K_M ~5.7-bit | ~33 GB | ~35 GB | 2×RTX 3090 or RTX A6000 (48 GB) |
| Q4_K_M ~4.8-bit | ~26 GB | ~28 GB | RTX 5090 (32 GB) |
How much VRAM do I need to run Mixtral 8x7B?
You need roughly ~28 GB of VRAM to run Mixtral 8x7B at Q4_K_M with an 8k-token context — that fits on RTX 5090 (32 GB). At Q8_0 plan for about ~52 GB, and full FP16 needs around ~95 GB. Mixtral is a Mixture-of-Experts model: only ~12.9B parameters are active per token (so it is fast), but all 46.7B must sit in memory. Fully on-GPU Q4_K_M needs ~29 GB; many people run it on a 24 GB card by offloading some layers to CPU RAM with llama.cpp, at reduced speed.
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.