← Back to community benchmarks

gemma-4-26b-a4b-it

M4 Max (40c) · 64 GB · 4bit · 2026-05-13
Performance
16k
tokens
1,373
PP tok/s
62.4
TG tok/s
11934
TTFT (ms)
31.3
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 16,384
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 current
32k 1,243 39.8 32.0 GB view
64k 1,029 10.1 33.8 GB view