← Back to community benchmarks
Qwen3.5-4B
Performance
1k
tokens
377.0
PP tok/s
38.0
TG tok/s
2716
TTFT (ms)
3.9
Peak mem (GB)
Hardware
Chip
M4
Memory
14 GB
Software
oMLX
v0.2.7
macOS
macOS 26.2
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 377.0 | 38.0 | 3.9 GB | current |
| 4k | 365.9 | 35.8 | 4.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 38.0 | 1.00× |
| 2× | 62.0 | 1.63× |
| 4× | 89.6 | 2.36× |