← Back to community benchmarks

gemma-4-26B-A4B-it-qat

M5 Max (40c) · 128 GB · 8bit · 2026-07-23
Performance
8k
tokens
3,659
PP tok/s
78.9
TG tok/s
2239
TTFT (ms)
26.7
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.5.3
macOS macOS 26.5.1
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
8k 3,659 78.9 26.7 GB current
64k 2,556 53.3 38.7 GB view