← Back to community benchmarks

community:gemma-4-26b-a4b-it

M4 Max (40c) · 48 GB · 4bit · 2026-04-15
Performance
32k
tokens
1,220
PP tok/s
39.8
TG tok/s
26849
TTFT (ms)
16.0
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 48 GB
GPU Cores 40
Software
oMLX v0.3.4
macOS macOS 26.4.1
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,204 103.7 14.2 GB view
32k 1,220 39.8 16.0 GB current
128k 719.4 5.8 21.2 GB view
Batching Results
Batch Size TG tok/s Speedup
103.7 1.00×
153.5 1.48×