← Back to community benchmarks

gemma-4-26b-a4b

M5 (10c) · 32 GB · 4bit · 2026-05-19
Performance
1k
tokens
762.3
PP tok/s
40.7
TG tok/s
1345
TTFT (ms)
13.5
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 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 762.3 40.7 13.5 GB current
4k 986.6 39.6 14.2 GB view
32k 834.6 28.0 15.5 GB view
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×