← Back to community benchmarks

gemma-4-26B-A4B-it-oQ8

M4 Pro (20c) · 64 GB · 8bit · 2026-05-01
Performance
16k
tokens
685.4
PP tok/s
32.7
TG tok/s
23903
TTFT (ms)
26.7
Peak mem (GB)
Hardware
Chip M4 Pro (20c)
Memory 64 GB
GPU Cores 20
Software
oMLX v0.3.7
macOS macOS 26.3.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 679.0 45.3 25.8 GB view
4k 734.2 43.8 26.2 GB view
8k 728.6 41.5 26.3 GB view
16k 685.4 32.7 26.7 GB current