← Back to community benchmarks

gemma-4-26B-A4B-it

M4 Max (40c) · 128 GB · 4bit · 2026-04-18
Performance
32k
tokens
1,160
PP tok/s
39.3
TG tok/s
28246
TTFT (ms)
16.0
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.6
macOS macOS 26.3.1
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,154 103.7 14.2 GB view
4k 1,363 94.5 14.7 GB view
8k 1,345 84.8 14.8 GB view
16k 1,265 71.0 15.2 GB view
32k 1,160 39.3 16.0 GB current
Batching Results
Batch Size TG tok/s Speedup
103.7 1.00×
149.5 1.44×
198.4 1.91×
242.7 2.34×