← Back to community benchmarks
Qwen3___5-2B
Performance
4k
tokens
773.2
PP tok/s
5.3
TG tok/s
5298
TTFT (ms)
6.9
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.2.6
macOS
macOS 26.4
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 636.7 | 5.3 | 6.8 GB | view |
| 4k | 773.2 | 5.3 | 6.9 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 5.3 | 1.00× |
| 2× | 10.4 | 1.96× |
| 4× | 20.4 | 3.85× |