← Back to community benchmarks

gemma-4-26b-a4b-it

M1 Max (24c) · 32 GB · 4bit · 2026-04-12
Performance
32k
tokens
347.1
PP tok/s
19.5
TG tok/s
94408
TTFT (ms)
15.3
Peak mem (GB)
Hardware
Chip M1 Max (24c)
Memory 32 GB
GPU Cores 24
Software
oMLX v0.3.4
macOS macOS 15.7.5
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 335.5 44.7 13.5 GB view
32k 347.1 19.5 15.3 GB current
Batching Results
Batch Size TG tok/s Speedup
44.7 1.00×
57.6 1.29×
75.9 1.70×