← CanIRunLocal · All hardware · All models

Can a Mac Studio M3 Ultra (80c GPU) 256GB run Ling-3.1-flash 560B-A25B (MoE)?

No. Ling-3.1-flash 560B-A25B (MoE) does not fit on Mac Studio M3 Ultra (80c GPU) 256GB: Q4_K_M needs 360.3 GB and 192.0 GB is usable.

Hardware: Mac Studio M3 Ultra (80c GPU) 256GB · Model: Ling-3.1-flash 560B-A25B (MoE)

Mac Studio M3 Ultra (80c GPU) 256GB has 256 GB of unified memory and 819 GB/s of memory bandwidth. Mac Studio M3 Ultra (60c GPU) 256GB has the same memory and bandwidth, so the fit numbers match; this page is Mac Studio M3 Ultra (80c GPU) 256GB. The checker leaves macOS a share of unified memory, so Ollama can use 192.0 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 quantQ4_K_M
Download size357.97 GB
Memory needed360.3 GB
Usable fast memory192.0 GB
Fitdoes not fit
Estimated speedno estimate, it does not fit
Commandollama run hf.co/bartowski/Ling-3.1-flash-GGUF:Q4_K_M

Smallest hardware that runs it: 4x Mac Studio M5 Max (40c GPU) 128GB at Q4_K_M (fits in fast memory, 360.3 GB needed, 378.0 GB usable, about 34 tok/s (estimate)).

No smaller inclusionAI model in this list fits Mac Studio M3 Ultra (80c GPU) 256GB.

Open Mac Studio M3 Ultra (80c GPU) 256GB in the checker

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