← CanIRunLocal · All hardware · All models
Yes. Qwen3-VL 4B fits in fast memory on M3 Max (40c GPU) 64GB at Q8_0 (6.3 GB needed, 48.0 GB usable), about 63 tok/s (estimate).
Hardware: M3 Max (40c GPU) 64GB · Model: Qwen3-VL 4B
M3 Max (40c GPU) 64GB has 64 GB of unified memory and 400 GB/s of memory bandwidth. M1 Max (32c GPU) 64GB and M2 Max (30c GPU) 64GB and M2 Max (38c GPU) 64GB have the same memory and bandwidth, so the fit numbers match; this page is M3 Max (40c GPU) 64GB. The checker leaves macOS a share of unified memory, so Ollama can use 48.0 GB. Qwen3-VL 4B (4.44B, Alibaba) at Q8_0 is a 5.1 GB download and needs 6.3 GB with headroom for about 8k tokens.
| Best quant | Q8_0 |
|---|---|
| Download size | 5.1 GB |
| Memory needed | 6.3 GB |
| Usable fast memory | 48.0 GB |
| Fit | fits in fast memory |
| Estimated speed | ~63 tok/s (estimate) |
| Command | ollama run qwen3-vl:4b-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