← Back to community benchmarks

gemma-4-26b-a4b-it

M4 (10c) · 32 GB · 4bit · 2026-04-18
Performance
8k
tokens
373.0
PP tok/s
27.8
TG tok/s
21962
TTFT (ms)
14.8
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 32 GB
GPU Cores 10
Software
oMLX v0.3.6
macOS macOS 26.3.1
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 373.1 34.7 14.2 GB view
4k 376.0 33.3 14.6 GB view
8k 373.0 27.8 14.8 GB current