← CanIRunLocal · All hardware · All models
Yes. Qwen3-VL 2B fits in fast memory on M2 Max (38c GPU) 96GB at Q8_0 (3.8 GB needed, 72.0 GB usable), about 119 tok/s (estimate).
Hardware: M2 Max (38c GPU) 96GB · Model: Qwen3-VL 2B
M2 Max (38c GPU) 96GB has 96 GB of unified memory and 400 GB/s of memory bandwidth. The checker leaves macOS a share of unified memory, so Ollama can use 72.0 GB. Qwen3-VL 2B (2.13B, Alibaba) at Q8_0 is a 2.7 GB download and needs 3.8 GB with headroom for about 8k tokens.
| Best quant | Q8_0 |
|---|---|
| Download size | 2.7 GB |
| Memory needed | 3.8 GB |
| Usable fast memory | 72.0 GB |
| Fit | fits in fast memory |
| Estimated speed | ~119 tok/s (estimate) |
| Command | ollama run qwen3-vl:2b-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