← Back to community benchmarks
Qwen3.5-2B
Performance
1k
tokens
922.7
PP tok/s
90.8
TG tok/s
1110
TTFT (ms)
3.1
Peak mem (GB)
Hardware
Chip
M2 Pro (19c)
Memory
16 GB
GPU Cores
19
Software
oMLX
v0.2.6
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 922.7 | 90.8 | 3.1 GB | current |
| 4k | 951.5 | 87.1 | 3.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 90.8 | 1.00× |
| 2× | 129.4 | 1.43× |
| 4× | 136.9 | 1.51× |
| 8× | 143.4 | 1.58× |