← Back to community benchmarks

gemma-4-26B-A4B-it-oQ3.5

M4 (10c) · 24 GB · 3bit · 2026-04-05
Performance
4k
tokens
378.5
PP tok/s
35.1
TG tok/s
10821
TTFT (ms)
12.8
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 24 GB
GPU Cores 10
Software
oMLX v0.3.4
macOS macOS 26.4
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 367.0 37.2 12.4 GB view
4k 378.5 35.1 12.8 GB current
Batching Results
Batch Size TG tok/s Speedup
37.2 1.00×
50.7 1.36×
58.2 1.56×