Albireo

Your private AI assistant, running on your own computer

Albireo runs language models directly on your Windows 11 computer. Your conversations, documents and models stay on the machine: no account to create, nothing sent outside.

  • Free
  • Open source
  • Windows 11, x64
  • Works offline
  • Version 1.0.23
  • Released 15 November 2026
  • License Boost Software License 1.0
A question about a chart, answered by the model that comes with Albireo
56.8
tokens per second on a laptop GPU, against 23.6 on its processor
22
models in the signed catalog, from 7 publishers
5
engines: processors, Intel NPU and GPU, NVIDIA GPU
0
account, subscription or data sent outside

The strengths of Albireo

Private by design

The service listens on the local address only. A question, a document or an image leaves the computer only if you switch the relay on.

Fast on the hardware you have

Its engine runs quantized models with integer kernels and takes advantage of the Intel NPU and GPU, or of an NVIDIA card, when the computer has one.

Up and running in minutes

The complete installer ships with its models: Albireo answers as soon as the installation ends, even without a connection.

Compatible with your tools

The local interface follows the OpenAI interface: your client libraries, editors and scripts work unchanged.

Every function of an assistant, running locally

Chat
Discussions kept in the browser, an incognito mode, a search across the discussions, and the reasoning of the models that reason shown while they think.
Documents
Word, Excel, PowerPoint, OpenDocument, PDF, RTF, HTML, text, CSV, Markdown and source code, read in the browser and attached to a message or a project.
Images
The models that read images take PNG and JPEG pictures, attached, pasted or dropped into a question.
Projects
Discussions grouped with instructions and documents that form their shared context, searched by meaning and by words.
Agent mode
The model calls tools that run in the page: calculator, sandboxed JavaScript, reading and search of the documents, up to 100 steps per answer.
Web access
An optional search of Wikipedia and the reading of public pages and PDF files, off in each new discussion.
Reading aloud
Each answer can be read aloud by the speech synthesis that comes with Albireo, without network.
An interface for other programs
Chat completions, completions, embeddings, speech and models follow the OpenAI interface, with streaming and images, documented in a Swagger page.
Offline mode
On a computer without network, the service opens no connection: the catalog, the models and the updates come from a signed bundle brought on a disk.
Relay to an external engine
A discussion can be relayed to an external engine: any interface compatible with OpenAI, the cloud of Ollama or Claude. Its texts are pseudonymized by Pseudalis before they leave the computer, and an engine of the computer or of the local network remains usable offline.

The model catalog of Albireo

Albireo runs nearly any open-weight language model published in the GGUF format, in both of today's main structures: dense models, where every parameter works for each token, and mixture-of-experts models, where a router activates a few experts. The catalog below lists the 22 models tested and offered for download, each checked by its hash.

Dense models

Architectures llama, mistral, mistral3, granite, phi3, qwen2, qwen3 and qwen3vl.

Mixture-of-experts models

Architectures mixtral, granitemoe, qwen3moe and qwen3vlmoe.

ModelPublisherFunctionsReadsSizeLicenseOfficial source
Qwen3-VL 4B Instruct defaultAlibabageneral, code, securitytext, images2.95 GBApache-2.0Hugging Face
Qwen3-VL 4B ThinkingAlibabageneral, code, securitytext, images2.95 GBApache-2.0Hugging Face
Qwen3-VL 2B ThinkingAlibabageneral, code, securitytext, images1.55 GBApache-2.0Hugging Face
Qwen3 Embedding 0.6B defaultAlibabadocument searchtext639.2 MBApache-2.0Hugging Face
Qwen3-VL 2B InstructAlibabageneraltext, images1.55 GBApache-2.0Hugging Face
Qwen3-VL 8B InstructAlibabageneral, code, securitytext, images5.78 GBApache-2.0Hugging Face
Qwen3-VL 8B ThinkingAlibabageneral, code, securitytext, images5.78 GBApache-2.0Hugging Face
EuroVLM 9B PreviewEuroLLM consortiumgeneraltext, images6.42 GBApache-2.0Hugging Face
Phi-4-miniMicrosoftgeneraltext2.49 GBMITHugging Face
Ministral 3 3BMistral AIgeneraltext, images2.99 GBApache-2.0Hugging Face
Ministral 3 8BMistral AIgeneraltext, images6.06 GBApache-2.0Hugging Face
EuroLLM 9B InstructEuroLLM consortiumgeneraltext5.58 GBApache-2.0Hugging Face
Granite 4.2 3BIBMgeneral, codetext2.24 GBApache-2.0Hugging Face
Granite 4.2 8BIBMgeneral, codetext5.35 GBApache-2.0Hugging Face
Qwen3-VL 30B A3B ThinkingAlibabageneral, code, securitytext, images19.27 GBApache-2.0Hugging Face
Mistral Small 3.2 24BMistral AIgeneraltext, images15.21 GBApache-2.0Hugging Face
Qwen2.5 Coder 1.5BAlibabacodetext1.12 GBApache-2.0Hugging Face
Qwen2.5 Coder 7BAlibabacodetext4.68 GBApache-2.0Hugging Face
Devstral Small 2Mistral AIcodetext, images15.21 GBApache-2.0Hugging Face
CyberSecQwen 4Bathena129 (lablab.ai)securitytext2.50 GBApache-2.0Hugging Face
Foundation-Sec 1.1 8BCiscosecuritytext4.92 GBLlama 3.1 Community LicenseHugging Face
Foundation-Sec 8B ReasoningCiscosecuritytext4.92 GBLlama 3.1 Community LicenseHugging Face

Sizes count the decoder and its image encoder. Each model keeps the license of its publisher.

Suggest a model to support

Speed on everyday hardware: the techniques of Albireo

Albireo runs models with its own engine, designed for the processors and graphics cards already in service. Each technique below is measured in the README of the product.

Quantized kernels

The weights stay in the memory mapping of the GGUF file, in their quantized form. Integer kernels compute 32 products where a vector of floats computes 8.

Reading a prompt: 216 tokens per second for Qwen3-VL 4B and more than 1,300 for Qwen3 0.6B (Intel Core Ultra 9 275HX, 24 threads); on two cores, 230 against 126 on floats (Qwen3 0.6B, AVX-VNNI)

Drafted tokens

An answer writes several tokens per step when its context foretells them, a form of speculative decoding. The model keeps the tokens it would have drawn itself, so that the answers keep the distribution of the sampling.

25.5 against 19.7 tokens per second when rewriting code (Qwen3 0.6B, two cores); 26.3 against 23.6 on 24 threads (Qwen3-VL 4B)

An engine for each kind of processor

Portable, AVX2 and AVX-VNNI engines for processors, the NPU and the integrated GPU of Intel through OpenVINO, NVIDIA graphics processors through CUDA. The service measures them on the machine and runs the fastest.

Writing: 80.6 to 87.7 tokens per second for Qwen3 0.6B with the processor engine (Intel Core Ultra 9 275HX, 24 threads)

Layers computed on the NVIDIA card

The CUDA engine keeps the weights on the card in their GGUF formats and computes the layers of a dense model there, attention included for the generated tokens.

56.8 against 23.6 tokens per second (Qwen3-VL 4B, RTX 5070 Ti Laptop GPU against 24 threads)

V²RAM extended memory

The extended device memory of the library lets the copies of the weights go beyond the memory of the card, into host memory or a file, and brings them back ahead of their use.

Compact conversation memory

Keys and values are kept in 8 bits, in pages shared between the conversations that start with the same text.

34 bytes against 64 per group of values, with the same next token on 210 positions

Several conversations at once

The requests of every client are computed together in each forward pass, and the keys and values of a finished request stay cached for the next turn.

32 to 40% less time per step with four answers written together

An OpenVINO graph on the Intel processor and GPU

With OpenVINO, a whole model is computed as a single graph on the processor or on the integrated GPU of Intel, and the NPU takes matrix products. The graph reads the first pass of a prompt faster; the processor engine stays faster on the following passes and when writing, and the measure of the engines, started from the tray icon, keeps the best choice for the machine.

First reading of a prompt: 260 tokens per second with the graph against 216 with the processor engine (Qwen3-VL 4B, Intel Core Ultra 9 275HX, 24 threads)

Engines
EngineRuns on
cpuEvery x86-64 processor
cpu-avx2Processors with AVX2, FMA and F16C: Intel Haswell, AMD Zen and later
cpu-avxvnniProcessors with AVX-VNNI: Intel Core from Alder Lake, Intel Xeon from Sapphire Rapids, AMD Zen 5
openvinoNPU and integrated GPU of Intel processors, through OpenVINO
cudaNVIDIA graphics processors, through CUDA

Screenshots

Audiences and uses of Albireo

Teams whose data must stay in-house

Legal, health, finance, public bodies and industry: questions about internal documents stay inside the organisation.

Developers

A local OpenAI-compatible endpoint for editors, scripts and tests, with code models in the catalog.

Security teams

Models specialised in cybersecurity, an offline mode and a signed bundle for isolated computers.

Integrators and software publishers

A component to embed or to distribute under their own brand, under a permissive licence.

Characteristics

PlatformWindows 11, x64
ProgramsInference engines, Windows service, web application, tray icon and installer
Model formatQuantized GGUF: Q4_0 to Q8_0, Q2_K to Q6_K and IQ4_NL
Architecturesllama, mistral, mistral3, granite, granitemoe, phi3, qwen2, qwen3, qwen3moe, qwen3vl, qwen3vlmoe, mixtral
Image encodersQwen3-VL, LLaVA-NeXT (EuroVLM) and Pixtral (Ministral 3, Devstral Small 2, Mistral Small 3.2)
Models that come with AlbireoQwen3-VL-4B-Instruct with its image encoder (2.95 GB) and Qwen3-Embedding-0.6B (0.64 GB)
Catalog22 models from 7 publishers, signed and checked against their hashes
ContextThe context window each model was trained for
Memory8 GB for the model installed by default
Local interfacehttps://localhost:8443, compatible with the OpenAI interface, documented with Swagger
Conversation formatsChatML, Mistral, Llama 3, Granite, Phi-4-mini and Foundation-Sec, written natively
Interface languagesEnglish, French, German, Italian and Spanish
UpdatesSigned feed, installers checked by size and SHA-256
LicenseBoost Software License 1.0, Community Edition

Security you can audit

Local only
The service listens on 127.0.0.1 and refuses the requests whose host or origin is not local.
A certificate authority of the computer
The HTTPS certificate comes from an authority made on the computer with an ECDSA P-256 key, restricted by name constraints to localhost.
Keys protected by Windows
The private key of the server and the key of the relay are encrypted with DPAPI and never written in clear.
A signed supply chain
The update feed and the model catalog are signed with ECDSA P-256, and every downloaded file is checked against its SHA-256.
An open interface
The routes follow the OpenAI interface and are described with OpenAPI, so that existing client libraries work unchanged.
Isolated speech synthesis
The synthesizer runs in a separate process of low integrity, without privileges and bounded in memory.

Good to know

Price and licence
Albireo Community is free, for personal and professional use, under the Boost Software License 1.0. Each model keeps the licence of its publisher.
Hardware
A Windows 11 x64 computer with 8 GB of memory runs the default model. A graphics card or an Intel NPU speeds it up and is not required.
Without a network
Everything works offline once the models are installed. An isolated computer receives the catalog, the models and the updates from a signed bundle.
Your data
Conversations are kept in the browser of the computer. The service reaches the outside only for updates, for the models you download, and for the web access or the relay you switch on.
Updates
The service reads a signed feed and verifies each installer by its size and its SHA-256 before installing it.

Installation

Each version comes with two installers. The complete installer ships with the models supplied with Albireo: the assistant answers as soon as the installation ends, without a connection. The online installer holds the same programs without the models: the service downloads the default models at its first start.

The wizard asks for the language, the license, the folders and the options. The command line covers silent deployments:

albireo-setup /silent [/dir <folder>] [/data-dir <folder>] [/models <folder>] [/port <port>] [/offline]
albireo-setup /uninstall [/silent] [/keep-data]
albireo-setup /models-dir <folder>
albireo-setup /service start|stop|restart
albireo-setup /lang en|fr|de|it|es

With Pseudalis on the same computer

The relay can pseudonymize every text before it is sent and restore the values in the answers as they stream. The table of substitutes stays in the memory of the service, and images never leave the computer: the local model describes them.

Install Albireo and ask your first question

The complete installer ships with its models: Albireo answers as soon as the installation ends.