# llama.cpp v b11806 adds LoRA weight support and new binaries

> The open‑source LLM runtime released new LoRA prism.hadamard weight support and binary packages for macOS, iOS and Linux on Oct 22 2026.

Oossa · 2026-10-22 · https://oossa.com/en/llama-cpp-v-b11806-adds-lora-weight-support-and-new-binaries

The ggml‑org team published llama.cpp version b11806. It adds LoRA support for prism.hadamard folded weights, a technique for more efficient fine‑tuning. The release also provides pre‑built binaries for Apple Silicon, Intel Macs, iOS, and several Linux builds including CPU, Vulkan and CUDA variants. Users can download the appropriate package from the GitHub release page.

## The facts

- Release version: b11806
- Published: Thu Oct 22 2026

## Why it matters

Developers can now run LoRA‑fine‑tuned models faster on more platforms without building the code themselves.

## Sources & references

1. [ggml-org/llama.cpp b11806](https://github.com/ggml-org/llama.cpp/releases/tag/b11806) – llama.cpp, 2026-10-22

Last updated: 2026-10-22