← Back to community benchmarks

gemma-4-26B-A4B-it-oQ4

M4 (10c) · 32 GB · 4bit · 2026-05-06
Performance
64k
tokens
244.7
PP tok/s
17.3
TG tok/s
267823
TTFT (ms)
17.8
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 32 GB
GPU Cores 10
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
4k 377.1 29.5 15.1 GB view
16k 344.3 27.0 15.7 GB view
32k 308.2 23.1 16.6 GB view
64k 244.7 17.3 17.8 GB current