← Back to community benchmarks
Qwen3.5-2B
Performance
4k
tokens
951.5
PP tok/s
87.1
TG tok/s
4305
TTFT (ms)
3.2
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
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 922.7 | 90.8 | 3.1 GB | view |
| 4k | 951.5 | 87.1 | 3.2 GB | current |
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× |