← Back to community benchmarks

Qwen3.5-27B

M1 Pro (16c) · 32 GB · 4bit · 2026-03-09
Performance
1k
tokens
45.2
PP tok/s
10.6
TG tok/s
22658
TTFT (ms)
16.6
Peak mem (GB)
Hardware
Chip M1 Pro (16c)
Memory 32 GB
GPU Cores 16
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 45.2 10.6 16.6 GB current
4k 45.0 10.1 17.0 GB view
Batching Results
Batch Size TG tok/s Speedup
10.6 1.00×
11.7 1.10×
12.0 1.13×