← Back to community benchmarks
Qwen3-4B
Performance
1k
tokens
701.6
PP tok/s
66.9
TG tok/s
1460
TTFT (ms)
2.9
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
64 GB
GPU Cores
40
Software
oMLX
v0.2.7
macOS
macOS 26.2
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 701.6 | 66.9 | 2.9 GB | current |
| 4k | 684.2 | 56.2 | 3.4 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 66.9 | 1.00× |
| 2× | 106.2 | 1.59× |
| 4× | 136.4 | 2.04× |
| 8× | 152.5 | 2.28× |