← Back to community benchmarks

gemma-3-27b-it-qat

M2 Max (30c) · 64 GB · 4bit · 2026-03-11
Performance
8k
tokens
86.3
PP tok/s
14.3
TG tok/s
94985
TTFT (ms)
18.0
Peak mem (GB)
Hardware
Chip M2 Max (30c)
Memory 64 GB
GPU Cores 30
Software
oMLX v0.2.7
macOS macOS 15.7.4
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 87.0 12.3 16.8 GB view
4k 86.5 16.0 17.7 GB view
8k 86.3 14.3 18.0 GB current
16k 85.3 11.1 18.6 GB view
32k 82.9 7.3 19.9 GB view
Batching Results
Batch Size TG tok/s Speedup
12.3 1.00×
109.9 8.93×
133.1 10.82×