← Back to community benchmarks

gemma-4-26b-a4b-it

M3 Max (30c) · 36 GB · 4bit · 2026-04-28
Performance
32k
tokens
704.2
PP tok/s
24.0
TG tok/s
46530
TTFT (ms)
16.0
Peak mem (GB)
Hardware
Chip M3 Max (30c)
Memory 36 GB
GPU Cores 30
Software
oMLX v0.3.7
macOS macOS 15.7.5
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 796.6 66.8 14.3 GB view
4k 891.7 63.1 14.7 GB view
8k 921.0 46.2 14.8 GB view
16k 851.1 37.8 15.2 GB view
32k 704.2 24.0 16.0 GB current
Batching Results
Batch Size TG tok/s Speedup
66.8 1.00×
100.0 1.50×
133.4 2.00×