← Back to community benchmarks

gemma-4-26b-a4b-it

M1 Max (32c) · 32 GB · 4bit · 2026-05-12
Performance
8k
tokens
499.0
PP tok/s
50.0
TG tok/s
16415
TTFT (ms)
15.5
Peak mem (GB)
Hardware
Chip M1 Max (32c)
Memory 32 GB
GPU Cores 32
Software
oMLX v0.3.9.dev1
macOS macOS 26.4.1
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 443.8 55.1 14.3 GB view
4k 497.5 52.5 15.1 GB view
8k 499.0 50.0 15.5 GB current
16k 486.2 45.1 16.1 GB view
32k 456.2 37.1 17.4 GB view
64k 395.3 24.2 20.1 GB view