← Back to community benchmarks

Qwen3.5-27B

M4 Max (40c) · 64 GB · 6bit · 2026-03-09
Performance
4k
tokens
235.0
PP tok/s
19.5
TG tok/s
17431
TTFT (ms)
23.2
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.2.6
macOS macOS 26.3
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 240.5 20.5 22.9 GB view
4k 235.0 19.5 23.2 GB current
Batching Results
Batch Size TG tok/s Speedup
20.5 1.00×
31.0 1.51×
28.6 1.40×