← Back to community benchmarks
Qwen3.5-4B
Performance
1k
tokens
375.0
PP tok/s
36.7
TG tok/s
2730
TTFT (ms)
3.3
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.3.6
macOS
macOS 26.2
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 375.0 | 36.7 | 3.3 GB | current |
| 4k | 386.5 | 35.2 | 3.9 GB | view |