← Back to community benchmarks
Qwen3___5-2B
Performance
4k
tokens
743.1
PP tok/s
4.9
TG tok/s
5512
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 | 632.7 | 5.0 | 6.9 GB | view |
| 4k | 743.1 | 4.9 | 6.9 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 5.0 | 1.00× |
| 2× | 10.1 | 2.02× |
| 4× | 20.0 | 4.00× |