← Back to community benchmarks

gemma-4-26B-A4B-it-mxfp4

M5 (10c) · 32 GB · 4bit · 2026-04-03
Performance
4k
tokens
1,021
PP tok/s
37.5
TG tok/s
4011
TTFT (ms)
14.7
Peak mem (GB)
Hardware
Chip M5 (10c)
Memory 32 GB
GPU Cores 10
Software
oMLX v0.3.2
macOS macOS 26.3
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,002 39.7 14.3 GB view
4k 1,021 37.5 14.7 GB current
Batching Results
Batch Size TG tok/s Speedup
39.7 1.00×
52.9 1.33×
63.6 1.60×