> ## Content Index
> Fetch the complete content index at: https://orbiorbi.com/news/llms.txt
> Use this file to discover other available public pages before exploring further.

# llama.cpp b11716 adds Hexagon Q1_0 and Q2_0 support
- URL: https://orbiorbi.com/news/en/hot/llama-cpp-b11716-hexagon-q1-q2-support-en/
- Published: 2026-10-17T21:15:22.000Z
- Updated: 2026-10-17T22:59:24.000Z
- Description: According to ggml's release notes, llama.cpp b11716 adds Q1_0 and Q2_0 quantization support to the Hexagon backend and enables Q1_0 weights in the 2D HMX matrix multiplication path.
- Author: Orbis News
- Tags: #orbis-hot, #en

According to ggml's release notes, llama.cpp b11716 adds Q1\_0 and Q2\_0 quantization support to the Hexagon backend and enables Q1\_0 weights in the 2D HMX matrix multiplication path.

- The update fixes MUL\_MAT\_NX's assumption of square tiling to accommodate the non-square tiles used by Q1 and Q2\. [\[1\]](#hot-source-1)

## Sources and originals

- \[1\] ggml · 2026-10-18 · [Read original](https://github.com/ggml-org/llama.cpp/releases/tag/b11716?ref=orbiorbi.com)  
ggml's release notes list two newly supported Hexagon quantization formats and a matrix multiplication fix.

{"version":2,"hot":{"event\_id":"llama-cpp-b11716-hexagon-q1-q2-support","group":"open-source","count":1,"heat":20,"verified":"confirmed","firstSeen":"2026-10-17T21:15:22.000Z","lastSeen":"2026-10-17T22:59:14.577Z","sources":\[{"n":"ggml","publisher":"ggml","u":"https://github.com/ggml-org/llama.cpp/releases/tag/b11716","say":"ggml's release notes list two newly supported Hexagon quantization formats and a matrix multiplication fix.","tier":"T0","at":"2026-10-17T21:15:22.000Z"}\],"signals":\[\],"facts":\["The update fixes MUL\_MAT\_NX's assumption of square tiling to accommodate the non-square tiles used by Q1 and Q2."\]}}