← Back to community benchmarks
Qwen3-0.6B
Performance
4k
tokens
864.1
PP tok/s
30.4
TG tok/s
4740
TTFT (ms)
5.3
Peak mem (GB)
Hardware
Chip
M1 (8c)
Memory
16 GB
GPU Cores
8
Software
oMLX
v0.2.9
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,098 | 41.8 | 4.8 GB | view |
| 4k | 864.1 | 30.4 | 5.3 GB | current |
| 8k | 713.9 | 22.5 | 5.6 GB | view |
| 16k | 479.7 | 13.6 | 6.5 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 41.8 | 1.00× |
| 2× | 42.9 | 1.03× |
| 4× | 72.7 | 1.74× |
| 8× | 124.6 | 2.98× |