← Back to community benchmarks

qw3.6-27b

M5 Max (40c) · 64 GB · 4bit · 2026-05-01
Performance
4k
tokens
874.4
PP tok/s
34.7
TG tok/s
4684
TTFT (ms)
16.5
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 815.4 35.6 15.1 GB view
4k 874.4 34.7 16.5 GB current
Batching Results
Batch Size TG tok/s Speedup
35.6 1.00×
54.8 1.54×
64.5 1.81×