← Back to community benchmarks

gemma-4-26b-a4b-it

M5 Pro (20c) · 64 GB · 4bit · 2026-05-13
Performance
64k
tokens
1,380
PP tok/s
35.5
TG tok/s
47476
TTFT (ms)
17.7
Peak mem (GB)
Hardware
Chip M5 Pro (20c)
Memory 64 GB
GPU Cores 20
Software
oMLX v0.3.8
macOS macOS 26.5
Context 65,536
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,509 74.6 14.3 GB view
4k 1,951 71.2 14.9 GB view
8k 2,048 65.9 15.1 GB view
16k 2,015 58.7 15.6 GB view
32k 1,805 48.7 16.0 GB view
64k 1,380 35.5 17.7 GB current
Batching Results
Batch Size TG tok/s Speedup
74.6 1.00×
107.8 1.45×
137.1 1.84×
164.5 2.21×