← CanIRunLocal · All hardware · All models
Yes. Gemma 4 26B-A4B (MoE) fits in fast memory on M3 Max (30c GPU) 96GB at Q8_0 (29.6 GB needed, 72.0 GB usable), about 29 tok/s (estimate).
Hardware: M3 Max (30c GPU) 96GB · Model: Gemma 4 26B-A4B (MoE)
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. Gemma 4 26B-A4B (MoE) (25.8B, 3.8B active, Google) at Q8_0 is a 28 GB download and needs 29.6 GB with headroom for about 8k tokens.
| Best quant | Q8_0 |
|---|---|
| Download size | 28 GB |
| Memory needed | 29.6 GB |
| Usable fast memory | 72.0 GB |
| Fit | fits in fast memory |
| Estimated speed | ~29 tok/s (estimate) |
| Command | ollama run gemma4:26b-a4b-it-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