← CanIRunLocal · All hardware · All models
Yes. Qwen 2.5 VL 7B fits in fast memory on M3 Max (30c GPU) 96GB at Q8_0 (10.8 GB needed, 72.0 GB usable), about 26 tok/s (estimate).
Hardware: M3 Max (30c GPU) 96GB · Model: Qwen 2.5 VL 7B
M3 Max (30c GPU) 96GB has 96 GB of unified memory and 300 GB/s of memory bandwidth. The checker leaves macOS a share of unified memory, so Ollama can use 72.0 GB. Qwen 2.5 VL 7B (8.29B, Alibaba) at Q8_0 is a 9.4 GB download and needs 10.8 GB with headroom for about 8k tokens.
| Best quant | Q8_0 |
|---|---|
| Download size | 9.4 GB |
| Memory needed | 10.8 GB |
| Usable fast memory | 72.0 GB |
| Fit | fits in fast memory |
| Estimated speed | ~26 tok/s (estimate) |
| Command | ollama run qwen2.5vl:7b-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