← Back to community benchmarks

gemma-4-26b-a4b-it

M4 Pro (16c) · 64 GB · 4bit · 2026-04-07
Performance
128k
tokens
315.8
PP tok/s
1.9
TG tok/s
414993
TTFT (ms)
21.2
Peak mem (GB)
Hardware
Chip M4 Pro (16c)
Memory 64 GB
GPU Cores 16
Software
oMLX v0.3.4
macOS macOS 26.3.1
Context 131,072
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 576.2 64.2 14.2 GB view
4k 612.9 59.9 14.7 GB view
8k 605.1 51.9 14.8 GB view
16k 573.9 35.5 15.2 GB view
32k 498.5 15.4 16.0 GB view
64k 428.4 5.9 17.7 GB view
128k 315.8 1.9 21.2 GB current
Batching Results
Batch Size TG tok/s Speedup
64.2 1.00×
84.7 1.32×