← Back to community benchmarks

gemma-4-26b-a4b-it

M3 Pro (18c) · 36 GB · 4bit · 2026-05-09
Performance
8k
tokens
567.7
PP tok/s
40.1
TG tok/s
14429
TTFT (ms)
14.8
Peak mem (GB)
Hardware
Chip M3 Pro (18c)
Memory 36 GB
GPU Cores 18
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
8k 567.7 40.1 14.8 GB current
16k 539.9 36.8 15.6 GB view
32k 482.9 32.4 16.5 GB view
64k 373.9 23.4 18.5 GB view