← Back to community benchmarks

Kimi-K2.6DQ3_K_M-q8

M3 Ultra (80c) · 512 GB · 4bit · 2026-05-25
Performance
32k
tokens
157.6
PP tok/s
16.3
TG tok/s
207907
TTFT (ms)
458.9
Peak mem (GB)
Hardware
Chip M3 Ultra (80c)
Memory 512 GB
GPU Cores 80
Software
oMLX v0.3.10
macOS macOS 26.4.1
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 222.8 22.1 439.6 GB view
4k 248.4 21.8 441.2 GB view
8k 232.1 21.0 443.7 GB view
16k 202.9 18.6 448.8 GB view
32k 157.6 16.3 458.9 GB current