← Back to community benchmarks

gemma-4-26B-A4B-it-OptiQ

M5 Pro (16c) · 48 GB · 4bit · 2026-05-03
Performance
16k
tokens
1,414
PP tok/s
55.4
TG tok/s
11584
TTFT (ms)
16.6
Peak mem (GB)
Hardware
Chip M5 Pro (16c)
Memory 48 GB
GPU Cores 16
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,091 60.0 15.3 GB view
4k 1,156 61.4 15.9 GB view
8k 1,404 58.1 16.1 GB view
16k 1,414 55.4 16.6 GB current
Batching Results
Batch Size TG tok/s Speedup
60.0 1.00×
84.8 1.41×
106.0 1.77×
119.8 2.00×