← Back to community benchmarks
Qwen3.5-4B
Performance
4k
tokens
489.7
PP tok/s
42.8
TG tok/s
8364
TTFT (ms)
4.2
Peak mem (GB)
Hardware
Chip
M3 Pro (14c)
Memory
18 GB
GPU Cores
14
Software
oMLX
v0.2.6
macOS
macOS 26.2
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 479.1 | 48.1 | 4.0 GB | view |
| 4k | 489.7 | 42.8 | 4.2 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 48.1 | 1.00× |
| 2× | 91.2 | 1.90× |
| 4× | 92.2 | 1.92× |