← Back to community benchmarks

gemma-4-26b-a4b

M5 (10c) · 32 GB · 4bit · 2026-05-19
Performance
32k
tokens
834.6
PP tok/s
28.0
TG tok/s
39264
TTFT (ms)
15.5
Peak mem (GB)
Hardware
Chip M5 (10c)
Memory 32 GB
GPU Cores 10
Software
oMLX v0.3.9.dev2
macOS macOS 26.4.1
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 762.3 40.7 13.5 GB view
4k 986.6 39.6 14.2 GB view
32k 834.6 28.0 15.5 GB current
64k 625.6 20.3 17.8 GB view
128k 444.7 12.6 22.0 GB view
Batching Results
Batch Size TG tok/s Speedup
40.7 1.00×
57.1 1.40×
68.6 1.69×