← Back to community benchmarks

gemma-4-26b-a4b-it

M2 Pro (16c) · 32 GB · 4bit · 2026-06-04
Performance
4k
tokens
265.8
PP tok/s
37.3
TG tok/s
15407
TTFT (ms)
14.9
Peak mem (GB)
Hardware
Chip M2 Pro (16c)
Memory 32 GB
GPU Cores 16
Software
oMLX v0.4.0
macOS macOS 26.5
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 255.9 39.3 14.3 GB view
4k 265.8 37.3 14.9 GB current
8k 271.4 35.5 15.1 GB view
16k 262.9 32.1 15.6 GB view
32k 244.1 24.5 16.5 GB view
64k 209.3 20.1 18.5 GB view
Batching Results
Batch Size TG tok/s Speedup
39.3 1.00×
80.9 2.06×