← Back to community benchmarks

gemma-4-26b-a4b-it

M2 (10c) · 24 GB · 4bit · 2026-05-01
Performance
1k
tokens
21.8
PP tok/s
3.6
TG tok/s
47053
TTFT (ms)
14.2
Peak mem (GB)
Hardware
Chip M2 (10c)
Memory 24 GB
GPU Cores 10
Software
oMLX v0.3.8
macOS macOS 26.3
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 21.8 3.6 14.2 GB current
4k 35.9 4.6 14.7 GB view
Batching Results
Batch Size TG tok/s Speedup
3.6 1.00×
8.2 2.28×
7.8 2.17×