# llama.cpp b11889: what's new, verdict & setup Canonical: https://theagenticweekly.com/tools/llama-cpp · Released: 2026-10-25 · Last verified: 2026-10-25 · Evidence: Tested (smoke test, 2026-10-25, local 3B model (Qwen2.5-3B)) · Vendor: ggml-org (open-source project) · Official site: https://github.com/ggml-org/llama.cpp > LLM inference in C/C++: the open-source engine many local-model tools build on; MIT-licensed with near-daily build tags. ## Verdict **LLM inference in C/C++: the open-source engine many local-model tools build on; MIT-licensed with near-daily build tags.** Good for: - Developers embedding local inference - People who want maximum control over local models Skip if: - You want a polished app with a GUI Tested. Tested 2026-10-25 (America/Chicago). llama.cpp b11889 generated 118 tokens/s (0.5B), 40 (1.5B) and 19.5 (3B) on 8 CPU threads with llama-bench, and its server passed the same prompts and tool call as Ollama. Test environment: Linux x86_64 virtual machine (Debian 13), 8 vCPU, 15 GiB RAM, no GPU; no vendor account, login or API key. Agent tools were pointed at a local open-weight model (Qwen2.5-3B-Instruct (Q4_K_M) through Ollama 0.40.11), so we tested the tool, not any vendor's hosted models. Not tested: Building from source, GPU backends, longer prompts, quantisations other than Q4_K_M, speculative decoding; Single bench run of 64 tokens; it is a smoke test and not a benchmark suite. These are smoke tests, not a benchmark. Full log: /tests/llama-cpp. Test scope: - Kind and date: smoke test, 2026-10-25 (America/Chicago). Not a benchmark. - What we ran: llama.cpp b11889 generated 118 tokens/s (0.5B), 40 (1.5B) and 19.5 (3B) on 8 CPU threads with llama-bench, and its server passed the same prompts and tool call as Ollama. - Model used: Qwen2.5-3B-Instruct (Q4_K_M) through Ollama 0.40.11 - Environment: Linux x86_64 virtual machine (Debian 13), 8 vCPU, 15 GiB RAM, no GPU; no vendor account, login or API key - Not tested: Building from source, GPU backends, longer prompts, quantisations other than Q4_K_M, speculative decoding; Single bench run of 64 tokens; it is a smoke test and not a benchmark suite. Full test log (commands, versions, raw output): [llama.cpp b11889 (commit d854d98ba): our test log](https://theagenticweekly.com/tests/llama-cpp) Pricing: Official page, dated. Open-source project; no pricing. (checked 2026-10-25) ## Best for - [Best AI tool for local LLM tools and model platforms](https://theagenticweekly.com/best/llm-platforms) (#-): C/C++ inference engine for running LLMs on local hardware. ## Key facts The llama.cpp repository describes LLM inference in C/C++ and is MIT-licensed. Its releases are build tags, with b11889 published Oct 25, 2026. - License: MIT (per GitHub) - Platforms: Cross-platform source and binaries - Pricing model: Free and open source - Free tier: Free - Paid plans: None - GitHub: ggml-org/llama.cpp: 132,360 stars on 2026-10-25, last push 2026-10-26 - Latest release we saw: b11889, 2026-10-25 - How to start: Clone the repository or download a release build and follow the README's quick start. - b11889 (2026-10-25): the newest release listed on the official page or repository when we read it on 2026-10-25. ## How to set it up: Get started with llama.cpp These steps come from the vendor's own pages as read on 2026-10-25.cpp. We ran llama.cpp on 2026-10-25; the test log lists what was and was not covered. 1. **Get access.** Clone the repository or download a release build and follow the README's quick start. 2. **Check the limits and costs first.** Free. Open-source project; no pricing. ## Pros and cons Pros: - MIT license - Very active Cons: - Command-line and build-oriented - Our test was one small task on a local 3B model; it does not show behaviour with hosted models or larger jobs ## Alternatives - [Ollama](https://theagenticweekly.com/tools/ollama): The common way to run open models locally on macOS, Windows and Linux, with a cloud option and an MIT-licensed open-source core. - [LM Studio](https://theagenticweekly.com/tools/lm-studio): Desktop app for running open models locally; the homepage now leads with Bionic, an agent for work and code. - [Jan](https://theagenticweekly.com/tools/jan): Open-source alternative to ChatGPT that runs open models locally or connects to cloud models like GPT and Claude. - [Cohere](https://theagenticweekly.com/tools/cohere): Enterprise AI company: Command models, Rerank and the North platform. - [DeepSeek](https://theagenticweekly.com/tools/deepseek): Model API that works with the OpenAI and Anthropic SDK formats and can back agent tools such as Claude Code, GitHub Copilot and OpenCode. - [Hugging Face](https://theagenticweekly.com/tools/hugging-face): The hub where the ML community shares models, datasets and apps, with PRO, Team and Enterprise tiers. - [LiteLLM](https://theagenticweekly.com/tools/litellm): Python SDK and proxy that gives one OpenAI-style interface to many model providers. - [Open WebUI](https://theagenticweekly.com/tools/open-webui): Self-hosted AI platform: a web interface that connects to Ollama and OpenAI-compatible models, under its own Open WebUI License. - [OpenRouter](https://theagenticweekly.com/tools/openrouter): Unified API to many models with fallbacks; a Free tier with 25+ free models and 4 free providers. - [Replicate](https://theagenticweekly.com/tools/replicate): Cloud API for running and fine-tuning open models, with per-use pricing. - [Together AI](https://theagenticweekly.com/tools/together-ai): AI cloud for open models: serverless inference, fine-tuning and GPU clusters, priced per token. - [GPT4All](https://theagenticweekly.com/tools/gpt4all): Local chatbot from Nomic that runs open-source models on your device; the latest GitHub release we saw is v3.10.0 from Feb 2025. ## FAQ ### What is llama.cpp? The llama.cpp repository describes LLM inference in C/C++ and is MIT-licensed. Its releases are build tags, with b11889 published Oct 25, 2026. ### Is llama.cpp free? Free. Open-source project; no pricing. Checked 2026-10-25; prices change, so confirm on the vendor's page. ### What license is llama.cpp under? Its license: MIT (per GitHub). Read from the project's own pages on 2026-10-25. ## What we have not verified - Performance on your hardware ## Sources - [llama.cpp repository (GitHub)](https://github.com/ggml-org/llama.cpp) (fetched 2026-10-25) ## How to cite Agentic Weekly, "llama.cpp b11889: what's new, verdict & setup", last updated 2026-10-25, https://theagenticweekly.com/tools/llama-cpp Keep the Reported or Tested label when you quote the verdict.