← Back to community benchmarks

gemma-4-26b-a4b-it

M5 Max (40c) · 128 GB · 4bit · 2026-04-03
Performance
1k
tokens
3,326
PP tok/s
85.1
TG tok/s
308
TTFT (ms)
15.1
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.2
macOS macOS 26.3.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 3,326 85.1 15.1 GB current
4k 3,296 80.9 15.4 GB view
8k 3,307 73.5 15.6 GB view
16k 3,329 65.4 16.1 GB view
32k 2,911 51.1 16.9 GB view
Batching Results
Batch Size TG tok/s Speedup
85.1 1.00×
113.0 1.33×
171.7 2.02×