← Back to community benchmarks

gemma-4-26b-a4b

M4 (10c) · 32 GB · 4bit · 2026-05-06
Performance
16k
tokens
305.0
PP tok/s
17.0
TG tok/s
53730
TTFT (ms)
14.4
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 32 GB
GPU Cores 10
Software
oMLX v0.3.6
macOS macOS 26.3.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 341.6 33.8 13.5 GB view
4k 348.6 31.4 13.9 GB view
8k 329.9 25.5 14.0 GB view
16k 305.0 17.0 14.4 GB current
32k 285.1 7.4 15.2 GB view
64k 232.1 3.1 16.9 GB view
Batching Results
Batch Size TG tok/s Speedup
33.8 1.00×
49.6 1.47×