← Back to community benchmarks

gemma-4-26b-a4b-it

M4 Max (40c) · 128 GB · 4bit · 2026-04-05
Performance
16k
tokens
1,280
PP tok/s
71.5
TG tok/s
12801
TTFT (ms)
14.5
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.4
macOS macOS 15.7.2
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,059 100.0 13.5 GB view
4k 1,298 94.3 14.0 GB view
8k 1,349 85.5 14.1 GB view
16k 1,280 71.5 14.5 GB current
Batching Results
Batch Size TG tok/s Speedup
100.0 1.00×
150.4 1.50×
200.1 2.00×