← Back to community benchmarks
Nanbeige4.1-3B
Performance
4k
tokens
487.4
PP tok/s
13.7
TG tok/s
8406
TTFT (ms)
8.0
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.2.9
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 485.6 | 14.3 | 7.7 GB | view |
| 4k | 487.4 | 13.7 | 8.0 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 14.3 | 1.00× |
| 2× | 18.2 | 1.27× |
| 4× | 35.6 | 2.49× |
| 8× | 68.3 | 4.78× |