← Back to community benchmarks
Qwen3.5-4B
Performance
4k
tokens
386.5
PP tok/s
35.2
TG tok/s
10597
TTFT (ms)
3.9
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.3.6
macOS
macOS 26.2
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 375.0 | 36.7 | 3.3 GB | view |
| 4k | 386.5 | 35.2 | 3.9 GB | current |