← Back to community benchmarks

gemma-4-26b-a4b-it

M4 Pro (20c) · 64 GB · 4bit · 2026-05-09
Performance
195k
tokens
296.7
PP tok/s
20.0
TG tok/s
674025
TTFT (ms)
27.7
Peak mem (GB)
Hardware
Chip M4 Pro (20c)
Memory 64 GB
GPU Cores 20
Software
oMLX v0.3.9.dev1
macOS macOS 26.4.1
Context 200,000
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 684.9 66.9 14.3 GB view
4k 743.9 64.2 14.9 GB view
8k 741.2 61.5 15.1 GB view
16k 699.0 54.8 15.6 GB view
32k 600.1 48.4 16.5 GB view
64k 512.2 38.3 18.5 GB view
128k 387.1 26.9 22.7 GB view
195k 296.7 20.0 27.7 GB current
Batching Results
Batch Size TG tok/s Speedup
66.9 1.00×
76.6 1.14×
114.3 1.71×