← Back to community benchmarks
Qwen3.5-2B
Performance
1k
tokens
914.5
PP tok/s
10.0
TG tok/s
1120
TTFT (ms)
7.1
Peak mem (GB)
Hardware
Chip
M2 Pro (16c)
Memory
16 GB
GPU Cores
16
Software
oMLX
v0.2.7
macOS
macOS 26.4
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 914.5 | 10.0 | 7.1 GB | current |
| 4k | 1,160 | 9.9 | 7.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 10.0 | 1.00× |
| 2× | 16.2 | 1.62× |
| 4× | 32.2 | 3.22× |