← Back to community benchmarks
Qwen3.5-4B4bit_副本
Performance
4k
tokens
629.0
PP tok/s
79.6
TG tok/s
6512
TTFT (ms)
4.1
Peak mem (GB)
Hardware
Chip
M4 Pro (16c)
Memory
24 GB
GPU Cores
16
Software
oMLX
v0.3.5
macOS
macOS 26.4.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 570.4 | 82.9 | 3.4 GB | view |
| 4k | 629.0 | 79.6 | 4.1 GB | current |