← Back to community benchmarks
Qwen3-4B
Performance
1k
tokens
406.7
PP tok/s
12.3
TG tok/s
2518
TTFT (ms)
8.0
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.2.11
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 406.7 | 12.3 | 8.0 GB | current |
| 4k | 381.2 | 11.3 | 8.5 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 12.3 | 1.00× |
| 2× | 15.2 | 1.24× |
| 4× | 29.5 | 2.40× |