Mistral on NVIDIA Blackwell
Can I run Mixtral 8x7B on an NVIDIA DGX Spark (GB10)?
Yes. Mixtral 8x7B at Q4_K_M uses 27.9 GB of the 96.0 GB available on a NVIDIA DGX Spark (GB10), and runs at about 19.7 tokens per second. You can push the context to 32K.
Runs comfortably
27.9 GB of 96.0 GB · 29%096 GB
Weights
26.4 GB
KV cache
1.0 GB
Runtime overhead
0.5 GB
Mixtral 8x7B at Q4_K_M leaves 68.1 GB spare on a NVIDIA DGX Spark (GB10). There is room to raise the context length or move up a quantisation level.
Generation19.7tok/s
Prompt processing2035tok/s
Max context32Ktokens
KV per 1K tokens0GB
Every quantisation of Mixtral 8x7B on a NVIDIA DGX Spark (GB10)
Highlighted row is the highest quality that still fits at 8K context.
| Quantisation | bpw | Weights | Total | Verdict | Max ctx | tok/s |
|---|---|---|---|---|---|---|
| FP16 / BF16 | 16.00 | 87.0 GB | 88.5 GB | Fits, but tight | 32K | 6.30 |
| INT8 / W8A8 | 8.50 | 46.2 GB | 47.7 GB | Runs comfortably | 32K | 11.6 |
| Q8_0 (GGUF) | 8.50 | 46.2 GB | 47.7 GB | Runs comfortably | 32K | 11.6 |
| FP8 (E4M3) | 8.00 | 43.5 GB | 45.0 GB | Runs comfortably | 32K | 12.3 |
| Q6_K | 6.56 | 35.7 GB | 37.2 GB | Runs comfortably | 32K | 14.8 |
| Q5_K_M | 5.67 | 30.8 GB | 32.3 GB | Runs comfortably | 32K | 17.0 |
| Q5_K_S | 5.52 | 30.0 GB | 31.5 GB | Runs comfortably | 32K | 17.4 |
| Q4_K_M | 4.85 | 26.4 GB | 27.9 GB | Runs comfortably | 32K | 19.7 |
| Q4_K_S | 4.58 | 24.9 GB | 26.4 GB | Runs comfortably | 32K | 20.7 |
| Q4_0 | 4.55 | 24.8 GB | 26.3 GB | Runs comfortably | 32K | 20.8 |
| AWQ 4-bit | 4.25 | 23.5 GB | 25.0 GB | Runs comfortably | 32K | 21.9 |
| GPTQ 4-bit | 4.25 | 23.5 GB | 25.0 GB | Runs comfortably | 32K | 21.9 |
| MXFP4 | 4.25 | 23.5 GB | 25.0 GB | Runs comfortably | 32K | 21.9 |
| IQ4_XS | 4.25 | 23.1 GB | 24.7 GB | Runs comfortably | 32K | 22.2 |
| Q3_K_M | 3.91 | 21.3 GB | 22.8 GB | Runs comfortably | 32K | 23.9 |
| IQ3_M | 3.70 | 20.2 GB | 21.7 GB | Runs comfortably | 32K | 25.1 |
| IQ3_XXS | 3.06 | 16.7 GB | 18.2 GB | Runs comfortably | 32K | 29.7 |
| Q2_K | 2.63 | 14.4 GB | 15.9 GB | Runs comfortably | 32K | 33.9 |
| IQ2_XXS | 2.06 | 11.3 GB | 12.8 GB | Runs comfortably | 32K | 41.6 |
| IQ1_M | 1.75 | 9.6 GB | 11.1 GB | Runs comfortably | 32K | 47.5 |