← Back to community benchmarks
Qwen3-8B
Performance
1k
tokens
218.9
PP tok/s
21.5
TG tok/s
4678
TTFT (ms)
4.9
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.2.19
macOS
macOS 26.3.1
Context
1,024
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 21.5 | 1.00× |
| 2× | 41.6 | 1.93× |
| 4× | 53.0 | 2.47× |
| 8× | 54.2 | 2.52× |