← Back to community benchmarks

Qwen3.5-27B

M2 Max (30c) · 64 GB · 4bit · 2026-03-09
Performance
1k
tokens
89.0
PP tok/s
13.2
TG tok/s
11500
TTFT (ms)
16.6
Peak mem (GB)
Hardware
Chip M2 Max (30c)
Memory 64 GB
GPU Cores 30
Software
oMLX v0.2.6
macOS macOS 26.3.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 89.0 13.2 16.6 GB current
4k 82.5 12.5 17.0 GB view
Batching Results
Batch Size TG tok/s Speedup
13.2 1.00×
16.6 1.26×
19.6 1.48×