← Back to community benchmarks

gemma-4-26B-A4B-it

M1 Pro (16c) · 32 GB · 4bit · 2026-05-02
Performance
64k
tokens
201.1
PP tok/s
10.2
TG tok/s
325939
TTFT (ms)
17.7
Peak mem (GB)
Hardware
Chip M1 Pro (16c)
Memory 32 GB
GPU Cores 16
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 65,536
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 236.3 37.4 14.3 GB view
4k 254.3 35.4 14.9 GB view
8k 254.2 33.2 15.1 GB view
16k 247.5 28.9 15.6 GB view
32k 230.9 17.1 16.5 GB view
64k 201.1 10.2 17.7 GB current
128k 149.7 7.6 21.2 GB view
Batching Results
Batch Size TG tok/s Speedup
37.4 1.00×
42.0 1.12×
48.2 1.29×