← CanIRunLocal · All hardware · All models
No. Llama 4 Scout 109B (MoE) does not fit on DGX Spark 64GB (ASUS, Dell, HP, MSI, Acer, Gigabyte): Q4_K_M needs 69.7 GB and 54.4 GB is usable.
Hardware: DGX Spark 64GB (ASUS, Dell, HP, MSI, Acer, Gigabyte) · Model: Llama 4 Scout 109B (MoE)
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. Llama 4 Scout 109B (MoE) (109B, 17B active, Meta) at Q4_K_M is a 67 GB download and needs 69.7 GB with headroom for about 8k tokens.
| Best quant | Q4_K_M |
|---|---|
| Download size | 67 GB |
| Memory needed | 69.7 GB |
| Usable fast memory | 54.4 GB |
| Fit | does not fit |
| Estimated speed | no estimate, it does not fit |
| Command | ollama run llama4:16x17b |
Smallest hardware that runs it: M2 Max (38c GPU) 96GB at Q4_K_M (fits in fast memory, 69.7 GB needed, 72.0 GB usable, about 15 tok/s (estimate)). Can a M2 Max (38c GPU) 96GB run Llama 4 Scout 109B (MoE)?
A smaller Meta model that fits this hardware: Llama 3.3 70B at Q5_K_M (fits in fast memory, 54.1 GB). Can a DGX Spark 64GB (ASUS, Dell, HP, MSI, Acer, Gigabyte) run Llama 3.3 70B?
Open DGX Spark 64GB (ASUS, Dell, HP, MSI, Acer, Gigabyte) in the checkerEstimates, 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