← Back to community benchmarks

Kimi-K2.6DQ3_K_M-q8

M3 Ultra (80c) · 512 GB · 4bit · 2026-05-25
Performance
4k
tokens
248.4
PP tok/s
21.8
TG tok/s
16489
TTFT (ms)
441.2
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 4,096
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 current
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 view