← Back to community benchmarks

gemma-4-26b-a4b-it

M1 Max (32c) · 64 GB · 4bit · 2026-04-06
Performance
4k
tokens
480.9
PP tok/s
48.7
TG tok/s
8518
TTFT (ms)
14.7
Peak mem (GB)
Hardware
Chip M1 Max (32c)
Memory 64 GB
GPU Cores 32
Software
oMLX v0.3.4
macOS macOS 26.2
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 419.6 53.1 14.2 GB view
4k 480.9 48.7 14.7 GB current
8k 491.9 42.3 14.8 GB view
Batching Results
Batch Size TG tok/s Speedup
53.1 1.00×
71.5 1.35×