← Back to community benchmarks
Mistral-Small-3.2-24B-Instruct-2506
Performance
16k
tokens
336.7
PP tok/s
23.5
TG tok/s
48670
TTFT (ms)
21.9
Peak mem (GB)
Hardware
Chip
M3 Ultra (60c)
Memory
256 GB
GPU Cores
60
Software
oMLX
v0.2.7
macOS
macOS 26.3.1
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 361.9 | 34.0 | 19.4 GB | view |
| 4k | 364.2 | 31.3 | 20.1 GB | view |
| 8k | 355.3 | 28.4 | 20.7 GB | view |
| 16k | 336.7 | 23.5 | 21.9 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 34.0 | 1.00× |
| 2× | 41.0 | 1.21× |
| 4× | 46.8 | 1.38× |