← Back to community benchmarks

gemma-4-26b-a4b-it-mxfp8

M5 Max (40c) · 128 GB · 8bit · 2026-04-12
Performance
8k
tokens
2,212
PP tok/s
64.6
TG tok/s
3704
TTFT (ms)
28.2
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.5.dev2
macOS macOS 26.5
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,059 64.8 27.5 GB view
4k 2,399 54.9 28.0 GB view
8k 2,212 64.6 28.2 GB current
Batching Results
Batch Size TG tok/s Speedup
64.8 1.00×
103.1 1.59×
141.2 2.18×