← Back to community benchmarks

gemma-4-26b-a4b-it

M4 Max (40c) · 128 GB · 8bit · 2026-04-13
Performance
1k
tokens
1,167
PP tok/s
67.3
TG tok/s
878
TTFT (ms)
26.4
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.5.dev1
macOS macOS 26.4.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,167 67.3 26.4 GB current
4k 1,375 66.3 26.9 GB view
8k 1,252 61.0 26.9 GB view
16k 1,084 52.2 27.3 GB view