← Back to community benchmarks

gemma-3-27b-it-qat

M3 Ultra (60c) · 256 GB · 6bit · 2026-03-19
Performance
8k
tokens
297.8
PP tok/s
22.7
TG tok/s
27512
TTFT (ms)
24.6
Peak mem (GB)
Hardware
Chip M3 Ultra (60c)
Memory 256 GB
GPU Cores 60
Software
oMLX v0.2.7
macOS macOS 26.3.1
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 296.6 24.1 23.3 GB view
4k 298.7 24.3 24.3 GB view
8k 297.8 22.7 24.6 GB current
16k 293.7 18.4 25.3 GB view
32k 286.9 12.2 26.5 GB view
Batching Results
Batch Size TG tok/s Speedup
24.1 1.00×
25.7 1.07×
32.5 1.35×