--- title: README emoji: 😻 colorFrom: yellow colorTo: blue sdk: static pinned: false short_description: Small, local models distilled from frontier teachers ---

Advanced Data Intelligence

Small, local, open models — distilled from frontier teachers.

ADI is a line of compact language models built at theLAB (Learning. Algorithms. Breakthroughs.). Each model is a knowledge distillation: a strong frontier "teacher" generates high-quality answers across thousands of prompts, and a small "student" model is fine-tuned to imitate them — producing a model that reasons and responds like something much larger, while staying small enough to run on a single consumer GPU.

Every model here is built end-to-end on theLAB hardware — no cloud training — then quantized to GGUF and shipped ready to run in Ollama or any llama.cpp-based runtime.

Links: Website · theLAB · YouTube — Advanced Data Intelligence · YouTube — ADI Online

New here? Start with one of these — adi-qwen3.5-4b, adi-qwen2.5-coder-7b, adi-qwen3-8b

### 🐱 adi-qwen3.5-4b-glm5.2-general General-purpose local assistant. Qwen3.5-4B distilled from **glm-5.2**. Reasons and explains like a frontier model on general topics. Native tool-calling, 262K context, ~2.7 GB. ```bash ollama run hf.co/AdvancedDataIntelligence/adi-qwen3.5-4b-glm5.2-general-GGUF:Q4_K_M ``` ### 🐱 adi-qwen3-8b-glm5.2-general General-purpose local assistant. Qwen3-8B distilled from **glm-5.2**. Reasons and explains like a frontier model on general topics, with more headroom than the 4B. Native tool-calling, 128K context, ~5 GB. ```bash ollama run hf.co/AdvancedDataIntelligence/adi-qwen3-8b-glm5.2-general-GGUF:Q4_K_M ``` ### 🐱 adi-qwen3.5-9b-glm5.2-general General-purpose local assistant. Qwen3.5-9B distilled from **glm-5.2**. The most capable general student in the line — more parametric headroom for nuanced reasoning while still fitting a single consumer GPU. Native tool-calling, 262K context, ~5.6 GB. ```bash ollama run hf.co/AdvancedDataIntelligence/adi-qwen3.5-9b-glm5.2-general-GGUF:Q4_K_M ``` ### 🐱 adi-qwen2.5-coder-7b-kimi2.7-code Local coding assistant. Qwen2.5-Coder-7B distilled from **kimi-k2.7-code**. Writes, explains, and debugs code with frontier-style quality. Native tool-calling, 128K context, ~4.4 GB. ```bash ollama run hf.co/AdvancedDataIntelligence/adi-qwen2.5-coder-7b-kimi2.7-code-GGUF:Q4_K_M ```

ADI model lineup — size on disk

---

Browse the whole line

ADI Models Lab — the full lineup in one place. Pick a student from the rail (Qwen3.5 4B, Qwen3.5 9B, Qwen3 8B, Coder 7B, and the hey-adi wakeword), read its teacher, context, and size at a glance, then copy a ready-to-paste run command. Includes the live in-browser demo — no install to try, no sign-in to copy.

Pick a student. Copy a command. Run offline.
▶ Open ADI Models Lab

---

Try it live

A hosted demo is available as a Hugging Face Space — chat with the model directly in your browser, no install required.

▶ Launch the demo

--- ## How to run **Ollama (recommended).** Pull and run any model directly from this org — no manual download needed. Ollama fetches the GGUF from Hugging Face on first run: ```bash ollama run hf.co/AdvancedDataIntelligence/adi-qwen3-8b-glm5.2-general-GGUF:Q4_K_M ``` Swap `:Q4_K_M` for another quant tag if a model ships multiple. To pull without running: ```bash ollama pull hf.co/AdvancedDataIntelligence/adi-qwen3-8b-glm5.2-general-GGUF:Q4_K_M ``` **Manual download (llama.cpp or offline).** Grab the raw GGUF with the Hugging Face CLI: ```bash huggingface-cli download AdvancedDataIntelligence/adi-qwen3-8b-glm5.2-general-GGUF adi-qwen3-8b-glm5.2-q4_k_m.gguf --local-dir . ``` Then point any llama.cpp-based runtime at the downloaded file.

## The approach - **Distillation, not retraining.** We transfer a teacher's reasoning style and answer quality into a small student — not net-new facts. For raw recall, pair these with retrieval (RAG). - **Local-first.** Every model runs fully offline on consumer hardware. No API, no data leaving the machine. - **Open.** Apache-2.0 where the base license allows, with full training details on each model card so the work is reproducible.

The ADI distillation pipeline

--- ## Coming next In the pipeline, distilled the same way and headed here soon: - **adi-qwen2.5-14b-glm5.2-general** — a larger general student with more parametric headroom. - **adi-gemma3-12b-glm5.2-general** — a Gemma-based general distill, broadening the lineup beyond Qwen. Follow the org to catch them on release. ## Naming Models follow the pattern `adi----` — so the name tells you the student base, its size, the teacher it learned from, and what it's tuned for.

ADI

Built at theLAB — Learning. Algorithms. Breakthroughs.