← Back to community benchmarks

gemma-4-26b-a4b-it

M4 (10c) · 24 GB · 4bit · 2026-04-20
Performance
1k
tokens
367.6
PP tok/s
34.1
TG tok/s
2786
TTFT (ms)
14.2
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 24 GB
GPU Cores 10
Software
oMLX v0.3.6
macOS macOS 26.2
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 367.6 34.1 14.2 GB current
4k 376.6 31.7 14.6 GB view
Batching Results
Batch Size TG tok/s Speedup
34.1 1.00×
49.6 1.45×
57.5 1.69×