← Back to community benchmarks

gemma-4-26b-a4b-it-4bit

M2 Pro (16c) · 32 GB · 4bit · 2026-06-04
Performance
16k
tokens
403.9
PP tok/s
36.2
TG tok/s
40568
TTFT (ms)
15.6
Peak mem (GB)
Hardware
Chip M2 Pro (16c)
Memory 32 GB
GPU Cores 16
Software
oMLX v0.4.0
macOS macOS 26.5
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 433.6 42.9 14.3 GB view
4k 418.0 40.8 14.9 GB view
8k 408.6 38.5 15.1 GB view
16k 403.9 36.2 15.6 GB current
32k 402.7 31.6 16.5 GB view
64k 329.4 25.2 18.5 GB view
Batching Results
Batch Size TG tok/s Speedup
42.9 1.00×
86.4 2.01×