← Back to community benchmarks

qw3.6-27b-mxfp8

M5 Max (40c) · 64 GB · 8bit · 2026-05-01
Performance
1k
tokens
702.2
PP tok/s
18.7
TG tok/s
1458
TTFT (ms)
27.6
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 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 702.2 18.7 27.6 GB current
4k 723.4 18.5 29.0 GB view
Batching Results
Batch Size TG tok/s Speedup
1× 18.7 1.00×
2× 29.3 1.57×
4× 35.0 1.87×