← Back to community benchmarks

Qwen3.5-4B-oQ4

M1 Max (32c) · 64 GB · 4bit · 2026-04-19
Performance
32k
tokens
466.4
PP tok/s
49.6
TG tok/s
70264
TTFT (ms)
6.8
Peak mem (GB)
Hardware
Chip M1 Max (32c)
Memory 64 GB
GPU Cores 32
Software
oMLX v0.3.6
macOS macOS 26.4.1
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
4k 879.6 71.9 4.2 GB view
32k 466.4 49.6 6.8 GB current