strix-nebulosa

llama.cpp lab for AMD Strix Halo — the owl that looks 180B and runs in 64 GB. Quants, dual-drafter routing, and NO-GOs published with the same care as the wins.

amd

View on GitHub

5 Stars

1 Forks

0 Watchers

C++ Language

other License

55.1 SrcLog Score

Cost to Build

$2.11M

Market Value

$2.17M

How is this calculated?

Growth over time

3 data points · 2026-09-06 → 2026-10-25

Stars Forks Watchers

💬

How do you feel about this project?

Ask AI about strix-nebulosa

Question copied to clipboard

What is the pugant/strix-nebulosa GitHub project? Description: "llama.cpp lab for AMD Strix Halo — the owl that looks 180B and runs in 64 GB. Quants, dual-drafter routing, and NO-GOs published with the same care as the wins.". Written in C++. Explain what it does, its main use cases, key features, and who would benefit from using it.