← Back to community benchmarks

gemma-4-26b-a4b-it

M2 Max (30c) · 64 GB · 8bit · 2026-05-15
Performance
16k
tokens
490.5
PP tok/s
44.3
TG tok/s
33402
TTFT (ms)
27.1
Peak mem (GB)
Hardware
Chip M2 Max (30c)
Memory 64 GB
GPU Cores 30
Software
oMLX v0.3.8
macOS macOS 26.5
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 435.5 53.6 25.8 GB view
4k 482.7 51.2 26.4 GB view
8k 503.3 48.5 26.6 GB view
16k 490.5 44.3 27.1 GB current
32k 460.2 36.5 28.0 GB view
64k 403.3 26.9 30.0 GB view
128k 323.0 17.8 32.7 GB view