← Back to community benchmarks

gemma-4-26b-a4b-it

M4 Pro (20c) · 64 GB · 4bit · 2026-06-04
Performance
32k
tokens
624.1
PP tok/s
46.5
TG tok/s
52508
TTFT (ms)
16.4
Peak mem (GB)
Hardware
Chip M4 Pro (20c)
Memory 64 GB
GPU Cores 20
Software
oMLX v0.4.1
macOS macOS 26.5.1
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 651.7 61.3 14.3 GB view
4k 725.6 59.8 15.0 GB view
32k 624.1 46.5 16.4 GB current
Batching Results
Batch Size TG tok/s Speedup
61.3 1.00×
85.1 1.39×
104.6 1.71×