← Back to community benchmarks

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

M4 Pro (20c) · 64 GB · 8bit · 2026-05-06
User commentwith dflash 8bit
Performance
16k
tokens
661.6
PP tok/s
39.9
TG tok/s
24763
TTFT (ms)
26.8
Peak mem (GB)
Hardware
Chip M4 Pro (20c)
Memory 64 GB
GPU Cores 20
Software
oMLX v0.3.8
macOS macOS 26.3
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
4k 345.5 44.0 26.2 GB view
8k 725.0 42.1 26.6 GB view
16k 661.6 39.9 26.8 GB current
32k 569.5 35.0 27.5 GB view
64k 481.8 26.5 29.2 GB view