← Back to community benchmarks
qwen3-8b
Performance
1k
tokens
349.7
PP tok/s
49.5
TG tok/s
2929
TTFT (ms)
5.0
Peak mem (GB)
Hardware
Chip
M4 Pro (16c)
Memory
24 GB
GPU Cores
16
Software
oMLX
v0.2.6
macOS
macOS 26.3
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 349.7 | 49.5 | 5.0 GB | current |
| 4k | 337.5 | 42.4 | 5.6 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 49.5 | 1.00× |
| 2× | 78.0 | 1.58× |
| 4× | 82.7 | 1.67× |