← Back to community benchmarks

gemma4H-26B-oQ8e

M3 Ultra (80c) · 512 GB · 8bit · 2026-07-17
Performance
16k
tokens
2,066
PP tok/s
65.9
TG tok/s
7930
TTFT (ms)
28.1
Peak mem (GB)
Hardware
Chip M3 Ultra (80c)
Memory 512 GB
GPU Cores 80
Software
oMLX v0.5.1
macOS macOS 26.5.2
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 2,422 76.7 25.8 GB view
4k 2,339 74.3 26.2 GB view
8k 2,201 70.6 27.0 GB view
16k 2,066 65.9 28.1 GB current
32k 1,848 56.8 30.2 GB view
64k 1,506 43.1 30.4 GB view
128k 1,066 28.6 34.4 GB view