CVE-2025-71439

published 27 Oct 2026 · updated 5 Nov 2026

llama.cpp before b5649 Heap Out-of-Bounds Read via llama_vocab::impl::print_info

5.5MediumCVSS 5.5EPSS 0%

No exploitation in the wild has been reported. EPSS puts the chance of exploitation in the next 30 days at 0%. Fixed in b5649.

llama.cpp before b5649 contains a heap out-of-bounds read vulnerability in llama_vocab::impl::print_info() that allows attackers to crash model loading via oversized special token IDs. Attackers can supply a crafted GGUF model with a short tokenizer.ggml.tokens array, causing llama-cli or llama-server to read past id_to_token and crash.

Affected

Vendors, products and packages with version ranges

VendorProductVersionsFixed
ggml-org<b5649b5649

Timeline

Every event on this vulnerability

Embed

A live severity badge for an advisory, README or ticket

CVE-2025-71439 severity on Zeptric[![CVE-2025-71439](https://zeptric.io/badge/cve/CVE-2025-71439.svg)](https://zeptric.io/cve/CVE-2025-71439)