← CanIRunLocal · All hardware · All models
Yes. Qwen3-VL 32B fits in fast memory on M2 Ultra 64GB at Q8_0 (38.6 GB needed, 48.0 GB usable), about 18 tok/s (estimate).
Hardware: M2 Ultra 64GB · Model: Qwen3-VL 32B
M2 Ultra 64GB has 64 GB of unified memory and 800 GB/s of memory bandwidth. The checker leaves macOS a share of unified memory, so Ollama can use 48.0 GB. Qwen3-VL 32B (33.4B, Alibaba) at Q8_0 is a 36 GB download and needs 38.6 GB with headroom for about 8k tokens.
| Best quant | Q8_0 |
|---|---|
| Download size | 36 GB |
| Memory needed | 38.6 GB |
| Usable fast memory | 48.0 GB |
| Fit | fits in fast memory |
| Estimated speed | ~18 tok/s (estimate) |
| Command | ollama run qwen3-vl:32b-instruct-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