← Back to community benchmarks

gemma-4-26B-A4B-it-unsloth

M5 Max (40c) · 128 GB · bf16 · 2026-05-10
Performance
195k
tokens
1,046
PP tok/s
19.3
TG tok/s
191223
TTFT (ms)
58.4
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 200,000
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
64k 2,520 39.6 51.3 GB view
128k 1,562 29.5 54.8 GB view
195k 1,046 19.3 58.4 GB current