# llama.cpp release b12343 adds Qwen 3.5 tensor merge

> The open‑source LLM runtime llama.cpp ships version b12343 with a new Qwen‑3.5 conversion tweak and binary builds for macOS, iOS and Linux.

Oossa · 2026-11-13 · https://oossa.com/en/llama-cpp-release-b12343-adds-qwen-3-5-tensor-merge

The ggml‑org team released llama.cpp version b12343 on 13 Nov 2026. The update merges tensors when converting Qwen‑3.5 models, simplifying model prep. It also drops a conversion test for that model. Pre‑built binaries are now available for Apple Silicon Macs, Intel Macs, iOS, and several Ubuntu CPU targets, including s390x and Vulkan builds.

## The facts

- Version b12343 released on 2026-11-13 ("Fri Nov 13 2026 06:23:01 GMT+0100")
- Adds Qwen 3.5 tensor‑merge on conversion

## Why it matters

Developers can now convert Qwen‑3.5 models faster and run llama.cpp on more Linux hardware without building from source.

## Sources & references

1. [ggml-org/llama.cpp b12343](https://github.com/ggml-org/llama.cpp/releases/tag/b12343) – llama.cpp, 2026-11-13

Last updated: 2026-11-13