← Back to community benchmarks
qwen3-8b
Performance
1k
tokens
347.4
PP tok/s
49.6
TG tok/s
2948
TTFT (ms)
5.0
Peak mem (GB)
Hardware
Chip
M4 Pro (16c)
Memory
24 GB
GPU Cores
16
Software
oMLX
v0.2.7
macOS
macOS 26.3
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 347.4 | 49.6 | 5.0 GB | current |
| 4k | 335.8 | 42.1 | 5.6 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 49.6 | 1.00× |
| 2× | 77.7 | 1.57× |
| 4× | 82.5 | 1.66× |