← Back to community benchmarks

gemma-4-26b-a4b-it-UD

M1 Pro (16c) · 32 GB · 4bit · 2026-04-24
Performance
32k
tokens
193.8
PP tok/s
5.9
TG tok/s
169044
TTFT (ms)
16.4
Peak mem (GB)
Hardware
Chip M1 Pro (16c)
Memory 32 GB
GPU Cores 16
Software
oMLX v0.3.7
macOS macOS 26.4.1
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 216.6 30.8 14.7 GB view
4k 213.0 28.6 15.2 GB view
8k 216.3 21.8 15.3 GB view
16k 213.0 14.0 15.7 GB view
32k 193.8 5.9 16.4 GB current
Batching Results
Batch Size TG tok/s Speedup
30.8 1.00×
34.2 1.11×
35.4 1.15×