Can I Run Devstral on NVIDIA DGX Spark?
Autor: Jakub Rusinowski · Ostatnia aktualizacja: 11 września 2026
Yes, comfortably — Devstral-2 123B at Q4_K_M needs 77.9 GB at 8K context (74.3 GB weights + 3.6 GB KV cache/overhead), leaving ~50.1 GB of the NVIDIA DGX Spark's 128 GB, at ~3 tok/s (est.), with room for up to 128K context.
See what else this hardware can run →
lub porównaj w Vast.ai od $0.77/godz. (typical low · varies)
Jako partner Amazon zarabiamy na kwalifikujących się zakupach. Linki do chmurowych GPU są linkami polecającymi — możemy otrzymać prowizję bez dodatkowych kosztów dla Ciebie.
NVIDIA DGX Spark Specs
| VRAM | 128 GB |
| Memory Bandwidth | 273 GB/s |
Devstral-2 123B on the NVIDIA DGX Spark: VRAM by quantization
| Quant | VRAM needed | Fits 128 GB? | Max context | Whole PC |
|---|---|---|---|---|
| F16 | 249.7 GB | ✗ No | — | — |
| Q8_0 | 134.4 GB | ✗ No | — | — |
| Q6_K | 104.5 GB | ✓ Yes | 64K | — |
| Q5_K_M | 90.9 GB | ✓ Yes | 64K | — |
| Q4_K_M | 77.9 GB | ✓ Yes | 128K | — |
| Q3_K_M | 56.1 GB | ✓ Yes | 128K | — |
| Q2_K | 44.1 GB | ✓ Yes | 128K | — |
Assumes an 8K-token context with an f16 KV cache, on an estimated architecture — this model publishes no config we can read. A longer window needs more; a quantized KV cache needs less. “Max context” is the largest window that still fits in 128 GB. Figures are estimates from parameter count, quantization and memory bandwidth — the analyzer lets you tune KV-cache quant and context.
Context costs VRAM too. At Q4_K_M on the NVIDIA DGX Spark: 8K 77.9 GB · 32K 86.6 GB · 128K 121.2 GB. Every window this model publishes still fits 128 GB.
No compatible GPU? Devstral on 16 GB of system RAM, CPU only: runs, but it is tight.
Devstral Sizes That Fit the NVIDIA DGX Spark (at 8K context)
| Devstral-2 123B | Q4_K_M · 77.9 GB at 8K context · ~3 tok/s (est.) |
| Devstral Small 2505 24B | Q4_K_M · 16.6 GB at 8K context · ~15 tok/s (est.) |
| Devstral Small 2 24B | Q4_K_M · 16.6 GB at 8K context · ~15 tok/s (est.) |
At 2 hrs/day, buying (~$4,699) beats renting at $0.77/hr after about 8.5 years.
Affiliate links — we may earn a commission if you sign up, at no extra cost to you.
Cloud rates verified 2026-07 — estimates, and marketplace prices vary. Buying price is GPU MSRP only, not a full PC.
FAQ
Devstral on the NVIDIA DGX Spark — does it fit?
Yes, comfortably — Devstral-2 123B at Q4_K_M needs 77.9 GB at 8K context (74.3 GB weights + 3.6 GB KV cache/overhead), leaving ~50.1 GB of the NVIDIA DGX Spark's 128 GB, at ~3 tok/s (est.), with room for up to 128K context.
Which Devstral variant fits best on the NVIDIA DGX Spark?
Devstral-2 123B at Q4_K_M quantization needs 77.9 GB at 8K context (74.3 GB weights + 3.6 GB KV cache/overhead), estimated ~3 tokens/sec, up to 128K context.
Every Devstral size on the NVIDIA DGX Spark
| Size | VRAM at 8K | Verdict | Speed |
|---|---|---|---|
| Devstral-2 123B | 77.9 GB | Runs | ~3 tok/s |
| Devstral Small 2505 24B | 16.6 GB | Runs | ~15 tok/s |
| Devstral Small 2 24B | 16.6 GB | Runs | ~15 tok/s |
Devstral on Other GPUs
- Devstral on Apple M4 Max
- Devstral on Apple M1 Ultra
- Devstral on Apple M5 Max
- Devstral on AMD Ryzen AI Max+ 395
Popular Models on the NVIDIA DGX Spark
VRAM Tier
Troubleshooting
Buying Guide
← Can I Run It? | Devstral Model Page | NVIDIA DGX Spark GPU Page | VRAM calculator | Check Your Hardware