← Back to community benchmarks
Qwen3.5-4B
Performance
4k
tokens
320.9
PP tok/s
35.2
TG tok/s
12766
TTFT (ms)
3.9
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.3.8
macOS
macOS 26.4.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 304.3 | 112.0 | 4.7 GB | view |
| 4k | 320.9 | 35.2 | 3.9 GB | current |