← Back to community benchmarks
Qwen3.5-2B
Performance
4k
tokens
2,058
PP tok/s
102.4
TG tok/s
1990
TTFT (ms)
3.6
Peak mem (GB)
Hardware
Chip
M4 Pro (20c)
Memory
24 GB
GPU Cores
20
Software
oMLX
v0.2.13
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,970 | 106.3 | 3.4 GB | view |
| 4k | 2,058 | 102.4 | 3.6 GB | current |
| 8k | 2,025 | 98.7 | 3.6 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 106.3 | 1.00× |
| 2× | 201.8 | 1.90× |
| 4× | 277.1 | 2.61× |
| 8× | 303.0 | 2.85× |