← Back to community benchmarks
Qwen3.5-2B
Performance
4k
tokens
632.0
PP tok/s
4.7
TG tok/s
6481
TTFT (ms)
6.9
Peak mem (GB)
Hardware
Chip
M2 (10c)
Memory
24 GB
GPU Cores
10
Software
oMLX
v0.2.6
macOS
macOS 15.3
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 505.4 | 4.7 | 6.8 GB | view |
| 4k | 632.0 | 4.7 | 6.9 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 4.7 | 1.00× |
| 2× | 8.6 | 1.83× |
| 4× | 17.7 | 3.77× |
| 8× | 33.2 | 7.06× |