← Back to community benchmarks
Qwen3.5-4B
Performance
8k
tokens
383.7
PP tok/s
33.4
TG tok/s
21348
TTFT (ms)
4.3
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.3.6
macOS
macOS 15.7.5
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 8k | 383.7 | 33.4 | 4.3 GB | current |
| 16k | 360.0 | 29.7 | 5.0 GB | view |