← Back to community benchmarks

gemma-4-26b-a4b-it

M4 Max (40c) · 64 GB · 4bit · 2026-05-13
Performance
32k
tokens
1,243
PP tok/s
39.8
TG tok/s
26357
TTFT (ms)
32.0
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.3.5.dev1
macOS macOS 26.3.1
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
8k 1,423 87.4 30.9 GB view
16k 1,373 62.4 31.3 GB view
32k 1,243 39.8 32.0 GB current
64k 1,029 10.1 33.8 GB view