← Back to community benchmarks

gemma-4-26b-a4b-it

M4 Max (40c) · 128 GB · bf16 · 2026-04-03
Performance
16k
tokens
1,365
PP tok/s
33.6
TG tok/s
12001
TTFT (ms)
49.8
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.1
macOS macOS 26.4
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,415 42.6 48.8 GB view
4k 1,414 41.4 49.2 GB view
8k 1,437 37.7 49.4 GB view
16k 1,365 33.6 49.8 GB current
32k 1,233 20.3 50.6 GB view
64k 1,013 12.0 52.3 GB view
Batching Results
Batch Size TG tok/s Speedup
42.6 1.00×
39.2 0.92×
72.3 1.70×