← Back to community benchmarks

gemma-4-26b-a4b-it

M2 Pro (16c) · 32 GB · 4bit · 2026-06-04
Performance
64k
tokens
209.3
PP tok/s
20.1
TG tok/s
313109
TTFT (ms)
18.5
Peak mem (GB)
Hardware
Chip M2 Pro (16c)
Memory 32 GB
GPU Cores 16
Software
oMLX v0.4.0
macOS macOS 26.5
Context 65,536
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 view
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 current
Batching Results
Batch Size TG tok/s Speedup
39.3 1.00×
80.9 2.06×