# llama.cpp update fixes Metal tensor error for large models

> The open‑source llama.cpp library adds a fix for a Metal GPU bug that broke large tensor multiplication, with new binaries for macOS, iOS and Linux.

Oossa · 2026-10-12 · https://oossa.com/en/llama-cpp-update-fixes-metal-tensor-error-for-large-models

The ggml‑org team released llama.cpp version b11575. The change fixes a Metal GPU kernel (kernel_mul_mm) that failed on large tensors. The fix is included in fresh binary packages for macOS Apple Silicon, macOS Intel, iOS, and several Ubuntu builds. The release was posted on GitHub on Oct 12, 2026.

## The facts

- Release version b11575, published Oct 12, 2026 – "Mon Oct 12 2026 22:43:00 GMT+0200"
- Fix targets Metal GPU kernel_mul_mm error for large tensors

## Why it matters

Developers can now run bigger language models on Apple Silicon Macs without GPU crashes.

## Sources & references

1. [ggml-org/llama.cpp b11575](https://github.com/ggml-org/llama.cpp/releases/tag/b11575) – llama.cpp, 2026-10-12

Last updated: 2026-10-12