Compatibility Check
Can I Run Devstral 2 123B on Apple M4 Ultra?
Yes — Apple M4 Ultra runs Devstral 2 123B fully on GPU at the Q8_0 quantization.
Estimated ~8.5 tokens/sec on the Q8_0 quantization.
Full GPU
Best variant: Q8_0
Full GPU inference — 256 GB VRAM meets the 159.9 GB recommendation.
- GPU VRAM
- 256 GB
- Min VRAM (best fit)
- 141.5 GB
- Recommended VRAM
- 159.9 GB
- Estimated tok/s
- ~8.5
Share this matchup
Send this page so a friend can see if Apple M4 Ultra fits Devstral 2 123B.
Every Devstral 2 123B quantization on Apple M4 Ultra
Each row runs the compatibility engine against your VRAM, RAM, and the model's requirements.
| Quantization | File Size | Min VRAM | Rec VRAM | Context | Verdict | Estimated tok/s |
|---|---|---|---|---|---|---|
| Q4_K_M | 61.5 GB | 70.7 GB | 80 GB | 8K / 8K | Full GPU | ~14.2 |
| Q5_K_M | 76.9 GB | 88.4 GB | 100 GB | 8K / 8K | Full GPU | ~12.3 |
| Q8_0Best fit | 123 GB | 141.5 GB | 159.9 GB | 8K / 8K | Full GPU | ~8.5 |
| FP16 | 246 GB | 282.9 GB | 319.8 GB | 8K / 8K | Can't Run | — |
Apple M4 Ultra is solid pick for Devstral 2 123B
Need second card or fresh build? These links help support site at no extra cost.