← Back to community benchmarks
Qwen3-4B
Performance
4k
tokens
744.4
PP tok/s
58.9
TG tok/s
5502
TTFT (ms)
3.4
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
64 GB
GPU Cores
40
Software
oMLX
v0.2.7
macOS
macOS 26.2
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 763.1 | 75.2 | 2.9 GB | view |
| 4k | 744.4 | 58.9 | 3.4 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 75.2 | 1.00× |
| 2× | 111.3 | 1.48× |
| 4× | 143.0 | 1.90× |