← Back to community benchmarks

gemma-4-26b-a4b-it

M5 Max (40c) · 128 GB · 4bit · 2026-05-10
Performance
4k
tokens
3,397
PP tok/s
109.3
TG tok/s
1206
TTFT (ms)
14.9
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 2,303 116.1 14.3 GB view
4k 3,397 109.3 14.9 GB current
8k 3,666 104.5 15.1 GB view
16k 3,490 92.3 15.6 GB view
32k 3,243 76.7 16.0 GB view
64k 2,426 56.5 17.7 GB view
128k 1,554 34.8 21.2 GB view
195k 1,057 25.5 25.0 GB view
Batching Results
Batch Size TG tok/s Speedup
116.1 1.00×
164.1 1.41×
209.8 1.81×