← Back to community benchmarks
Devstral-Small-2507
Performance
4k
tokens
101.7
PP tok/s
20.7
TG tok/s
40280
TTFT (ms)
14.1
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
64 GB
GPU Cores
32
Software
oMLX
v0.3.8
macOS
macOS 26.4.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 101.7 | 22.7 | 13.1 GB | view |
| 4k | 101.7 | 20.7 | 14.1 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 22.7 | 1.00× |
| 2× | 25.1 | 1.11× |
| 4× | 26.8 | 1.18× |