← CanIRunLocal · All hardware · All models
Yes. Qwen 2.5 72B fits in fast memory on DGX Spark 64GB (ASUS, Dell, HP, MSI, Acer, Gigabyte) at Q4_K_M (51.1 GB needed, 54.4 GB usable), about 4 tok/s (estimate).
Hardware: DGX Spark 64GB (ASUS, Dell, HP, MSI, Acer, Gigabyte) · Model: Qwen 2.5 72B
DGX Spark 64GB (ASUS, Dell, HP, MSI, Acer, Gigabyte) has 64 GB of unified memory and 273 GB/s of memory bandwidth. DGX OS keeps about 15% of unified memory, so Ollama can use 54.4 GB. Qwen 2.5 72B (72.7B, Alibaba) at Q4_K_M is a 47 GB download and needs 51.1 GB with headroom for about 8k tokens.
| Best quant | Q4_K_M |
|---|---|
| Download size | 47 GB |
| Memory needed | 51.1 GB |
| Usable fast memory | 54.4 GB |
| Fit | fits in fast memory |
| Estimated speed | ~4 tok/s (estimate) |
| Command | ollama run qwen2.5:72b |
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