← Back to community benchmarks

gemma-4-26b-a4b-it-oQ8

M5 Max (40c) · 128 GB · 8bit · 2026-05-25
Performance
32k
tokens
1,483
PP tok/s
41.7
TG tok/s
22092
TTFT (ms)
28.0
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.10
macOS macOS 26.4.1
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,967 50.6 25.8 GB view
4k 1,537 65.4 26.4 GB view
8k 1,620 60.9 26.6 GB view
16k 1,669 55.3 27.1 GB view
32k 1,483 41.7 28.0 GB current
64k 1,082 25.1 30.0 GB view