← CanIRunLocal · All hardware · All models
Yes. Ministral 3 3B fits in fast memory on DGX Spark 128GB (NVIDIA, ASUS, Dell, Lenovo, HP, MSI, Acer, Gigabyte) at Q8_0 (5.6 GB needed, 108.8 GB usable), about 46 tok/s (estimate).
Hardware: DGX Spark 128GB (NVIDIA, ASUS, Dell, Lenovo, HP, MSI, Acer, Gigabyte) · Model: Ministral 3 3B
DGX Spark 128GB (NVIDIA, ASUS, Dell, Lenovo, HP, MSI, Acer, Gigabyte) has 128 GB of unified memory and 273 GB/s of memory bandwidth. DGX OS keeps about 15% of unified memory, so Ollama can use 108.8 GB. Ministral 3 3B (3.85B, Mistral) at Q8_0 is a 4.5 GB download and needs 5.6 GB with headroom for about 8k tokens.
| Best quant | Q8_0 |
|---|---|
| Download size | 4.5 GB |
| Memory needed | 5.6 GB |
| Usable fast memory | 108.8 GB |
| Fit | fits in fast memory |
| Estimated speed | ~46 tok/s (estimate) |
| Command | ollama run ministral-3:3b-instruct-2512-q8_0 |
Estimates, not benchmarks. Model sizes are ollama.com download sizes; memory needed adds headroom for ~8k tokens of context; speeds are rough figures from memory bandwidth. Data updated 2026-10-23.
A project by OnDevice Labs · llms.txt