← Back to community benchmarks

gemma-4-26B-A4B-it

M4 Pro (20c) · 48 GB · 4bit · 2026-05-11
Performance
32k
tokens
631.9
PP tok/s
47.7
TG tok/s
51855
TTFT (ms)
16.7
Peak mem (GB)
Hardware
Chip M4 Pro (20c)
Memory 48 GB
GPU Cores 20
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 649.7 67.3 14.3 GB view
4k 720.0 64.1 15.0 GB view
8k 719.7 61.3 15.3 GB view
16k 705.3 56.1 15.8 GB view
32k 631.9 47.7 16.7 GB current
64k 516.7 39.7 18.6 GB view
Batching Results
Batch Size TG tok/s Speedup
67.3 1.00×
96.9 1.44×
116.5 1.73×