← Back to community benchmarks

Jackrong:Qwen3.5-27B-GLM5.1-Distill-v1-oQ8

M4 Max (40c) · 128 GB · 8bit · 2026-04-20
Performance
32k
tokens
225.0
PP tok/s
13.1
TG tok/s
145619
TTFT (ms)
34.2
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 128 GB
GPU Cores 40
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
1k 234.8 16.3 28.3 GB view
4k 244.4 15.9 29.8 GB view
8k 244.2 15.6 30.4 GB view
16k 237.9 14.5 31.7 GB view
32k 225.0 13.1 34.2 GB current
64k 195.6 10.8 39.2 GB view