← CanIRunLocal · All hardware · All models
Yes. Ling-3.1-flash 560B-A25B (MoE) fits in fast memory on Mac Studio M3 Ultra (80c GPU) 512GB at Q4_K_M (360.3 GB needed, 384.0 GB usable), about 20 tok/s (estimate).
Hardware: Mac Studio M3 Ultra (80c GPU) 512GB · Model: Ling-3.1-flash 560B-A25B (MoE)
Mac Studio M3 Ultra (80c GPU) 512GB has 512 GB of unified memory and 819 GB/s of memory bandwidth. The checker leaves macOS a share of unified memory, so Ollama can use 384.0 GB. Ling-3.1-flash 560B-A25B (MoE) (560B, 25B active, inclusionAI) at Q4_K_M is a 357.97 GB download and needs 360.3 GB with headroom for about 8k tokens.
| Best quant | Q4_K_M |
|---|---|
| Download size | 357.97 GB |
| Memory needed | 360.3 GB |
| Usable fast memory | 384.0 GB |
| Fit | fits in fast memory |
| Estimated speed | ~20 tok/s (estimate) |
| Command | ollama run hf.co/bartowski/Ling-3.1-flash-GGUF:Q4_K_M |
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