← Back to community benchmarks

gemma-4-26B-A4B-it-heretic

M4 Max (40c) · 128 GB · 4bit · 2026-05-04
Performance
8k
tokens
1,307
PP tok/s
88.0
TG tok/s
6268
TTFT (ms)
16.9
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.8rc1
macOS macOS 26.4.1
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,198 105.8 16.4 GB view
4k 1,403 99.8 16.9 GB view
8k 1,307 88.0 16.9 GB current
64k 825.1 33.3 19.8 GB view
Batching Results
Batch Size TG tok/s Speedup
105.8 1.00×
149.8 1.42×
190.5 1.80×