← Back to community benchmarks

gemma-4-26b-a4b-it

M1 Max (32c) · 64 GB · 4bit · 2026-05-05
Performance
32k
tokens
462.7
PP tok/s
35.4
TG tok/s
70819
TTFT (ms)
16.5
Peak mem (GB)
Hardware
Chip M1 Max (32c)
Memory 64 GB
GPU Cores 32
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 425.6 52.2 14.3 GB view
4k 499.8 50.1 14.8 GB view
8k 504.4 47.5 15.3 GB view
16k 494.0 42.9 15.6 GB view
32k 462.7 35.4 16.5 GB current
Batching Results
Batch Size TG tok/s Speedup
52.2 1.00×
69.2 1.33×
81.2 1.56×
94.6 1.81×