← Back to community benchmarks

gemma-4-12B-it-mxfp8

M5 Max (40c) · 64 GB · 8bit · 2026-06-09
Performance
4k
tokens
1,560
PP tok/s
35.7
TG tok/s
2626
TTFT (ms)
13.7
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.4.2
macOS macOS 26.5.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,276 44.0 12.6 GB view
4k 1,560 35.7 13.7 GB current
16k 1,442 35.0 14.1 GB view
Batching Results
Batch Size TG tok/s Speedup
44.0 1.00×
38.0 0.86×
44.8 1.02×