← Back to community benchmarks
Qwen3.5-4B-oQ6
Performance
4k
tokens
521.9
PP tok/s
58.5
TG tok/s
7848
TTFT (ms)
5.1
Peak mem (GB)
Hardware
Chip
M4 Pro (16c)
Memory
24 GB
GPU Cores
16
Software
oMLX
v0.3.6
macOS
macOS 26.4.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 521.3 | 189.2 | 5.9 GB | view |
| 4k | 521.9 | 58.5 | 5.1 GB | current |