← Back to community benchmarks

gemma-4-26b-a4b-it

M5 Max (32c) · 36 GB · 4bit · 2026-04-13
Performance
4k
tokens
2,231
PP tok/s
86.3
TG tok/s
1836
TTFT (ms)
14.7
Peak mem (GB)
Hardware
Chip M5 Max (32c)
Memory 36 GB
GPU Cores 32
Software
oMLX v0.3.5.dev1
macOS macOS 26.4.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,515 94.0 14.2 GB view
4k 2,231 86.3 14.7 GB current
Batching Results
Batch Size TG tok/s Speedup
1× 94.0 1.00×
2× 138.8 1.48×
4× 193.6 2.06×