← Back to community benchmarks

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

M4 (10c) · 32 GB · 3bit · 2026-05-06
Performance
16k
tokens
345.5
PP tok/s
31.2
TG tok/s
47426
TTFT (ms)
12.7
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 32 GB
GPU Cores 10
Software
oMLX v0.3.8
macOS macOS 26.3.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 364.6 37.7 11.4 GB view
4k 374.0 36.4 12.1 GB view
8k 365.6 34.7 12.2 GB view
16k 345.5 31.2 12.7 GB current
32k 305.2 24.8 13.6 GB view
64k 248.7 18.6 14.8 GB view
Batching Results
Batch Size TG tok/s Speedup
37.7 1.00×
51.9 1.38×
58.9 1.56×
64.2 1.70×