← Back to community benchmarks
North-Mini-Code-1.0
Performance
32k
tokens
1,262
PP tok/s
45.0
TG tok/s
25967
TTFT (ms)
20.0
Peak mem (GB)
Hardware
Chip
M5 Pro (16c)
Memory
48 GB
GPU Cores
16
Software
oMLX
v0.4.4
macOS
macOS 26.5.2
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,470 | 63.2 | 17.9 GB | view |
| 4k | 1,849 | 57.7 | 18.5 GB | view |
| 8k | 1,549 | 54.2 | 19.1 GB | view |
| 16k | 1,444 | 51.6 | 19.4 GB | view |
| 32k | 1,262 | 45.0 | 20.0 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 63.2 | 1.00× |
| 2× | 55.5 | 0.88× |
| 4× | 86.9 | 1.38× |
| 8× | 129.2 | 2.04× |