← Back to community benchmarks

gemma-4-26B-A4B-it-oQ3

M2 Max (30c) · 32 GB · 3bit · 2026-05-07
Performance
64k
tokens
478.5
PP tok/s
20.0
TG tok/s
136952
TTFT (ms)
14.8
Peak mem (GB)
Hardware
Chip M2 Max (30c)
Memory 32 GB
GPU Cores 30
Software
oMLX v0.3.8
macOS macOS 26.3.1
Context 65,536
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
8k 729.4 56.8 12.0 GB view
16k 683.6 52.3 12.4 GB view
32k 583.1 34.0 13.7 GB view
64k 478.5 20.0 14.8 GB current