← Back to community benchmarks

gemma-4-26b-a4b-it-UD

M3 Max (30c) · 36 GB · 3bit · 2026-07-13
Performance
32k
tokens
689.3
PP tok/s
46.1
TG tok/s
47536
TTFT (ms)
13.7
Peak mem (GB)
Hardware
Chip M3 Max (30c)
Memory 36 GB
GPU Cores 30
Software
oMLX v0.5.0
macOS macOS 26.5.1
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
32k 689.3 46.1 13.7 GB current
64k 541.2 38.9 16.8 GB view