← Back to community benchmarks

gemma-4-26b-a4b-it

M1 Pro (14c) · 32 GB · 4bit · 2026-06-04
Performance
64k
tokens
179.2
PP tok/s
11.7
TG tok/s
365615
TTFT (ms)
27.8
Peak mem (GB)
Hardware
Chip M1 Pro (14c)
Memory 32 GB
GPU Cores 14
Software
oMLX v0.4.1
macOS macOS 26.5
Context 65,536
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 216.0 32.8 14.3 GB view
4k 225.5 31.9 14.7 GB view
64k 179.2 11.7 27.8 GB current
Batching Results
Batch Size TG tok/s Speedup
32.8 1.00×
65.3 1.99×
135.6 4.13×