← Back to community benchmarks

gemma-4-26b-a4b-it

M4 Pro (16c) · 24 GB · 4bit · 2026-04-14
Performance
8k
tokens
608.7
PP tok/s
48.5
TG tok/s
13459
TTFT (ms)
14.8
Peak mem (GB)
Hardware
Chip M4 Pro (16c)
Memory 24 GB
GPU Cores 16
Software
oMLX v0.3.5
macOS macOS 26.3.1
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 584.4 65.3 14.2 GB view
4k 616.8 60.8 14.7 GB view
8k 608.7 48.5 14.8 GB current
16k 577.6 35.0 15.2 GB view
Batching Results
Batch Size TG tok/s Speedup
65.3 1.00×
85.4 1.31×
99.0 1.52×