← Back to community benchmarks

gemma-4-26b-a4b-it

M5 (10c) · 32 GB · 4bit · 2026-04-19
Performance
32k
tokens
854.9
PP tok/s
19.1
TG tok/s
38330
TTFT (ms)
15.9
Peak mem (GB)
Hardware
Chip M5 (10c)
Memory 32 GB
GPU Cores 10
Software
oMLX v0.3.6
macOS macOS 26.4.1
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 715.3 37.9 14.2 GB view
4k 946.7 38.5 14.7 GB view
8k 1,025 33.1 14.8 GB view
32k 854.9 19.1 15.9 GB current
Batching Results
Batch Size TG tok/s Speedup
37.9 1.00×
83.0 2.19×
163.2 4.31×