← Back to community benchmarks
Qwen3-4B-Instruct-2507
Performance
1k
tokens
3,672
PP tok/s
56.9
TG tok/s
279
TTFT (ms)
8.2
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.8
macOS
macOS 26.4.1
Context
1,024
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 56.9 | 1.00× |
| 2× | 57.3 | 1.01× |
| 4× | 105.6 | 1.86× |
| 8× | 198.1 | 3.48× |