ADI is a family of small, fully local models distilled from frontier teachers and served from Ollama across the fleet. The family is organized by line — one per student base model — and within each line, individual models are distilled from different teachers for different purposes. Every model fits on a single 16 GB GPU and runs offline.
Try the Models LabThe flagship line. Qwen3.5 students are strong general reasoners with native tool calling, and Unsloth's bf16 LoRA path handles their delta-net / Mamba-hybrid layers cleanly on a single card.
adi-qwen3.5-4b-glm5.2-general
Live
General-knowledge student distilled from glm-5.2. 2,068 distilled pairs, bf16 LoRA, quantized to a 2.7 GB q4_k_m GGUF. Reasons and answers like its frontier teacher.
adi-qwen3-8b-glm5.2-general
Live
The general-knowledge recipe scaled up to an 8B Qwen3 base for more headroom — same glm-5.2 teacher, more student capacity to absorb it. 4-bit QLoRA, quantized to a ~5 GB GGUF, 128K context.
adi-qwen3.5-9b-glm5.2-general
Live
A larger Qwen3.5 9B general-knowledge student distilled from glm-5.2. Published as a GGUF repo for local inference and comparison against the 4B and 8B general builds.
The Qwen2.5 base line. General-purpose Qwen2.5 students distilled from frontier teachers, offering a non-hybrid alternative to the Qwen3 line with broader community tooling support.
adi-qwen2.5-14b-glm5.2-general
Live
General-knowledge student distilled from glm-5.2 on a Qwen2.5 14B base. A mid-size build offering more capacity than the 4B/8B Qwen3 models while staying a single-GPU GGUF.
adi-qwen2.5-7b-ablit-glm5.2
Live
An abliterated Qwen2.5 7B student distilled from glm-5.2. Published as an uncensored GGUF variant for local experiments and comparison with the standard general line.
The coder line. Qwen2.5-Coder is a code-specialized base, distilled from a frontier coding teacher into a compact local model for software tasks and tool use.
A line built on Google's Gemma 4 base models — a different student family to compare distillation behavior and licensing against the Qwen3 line. The first build is in progress.
adi-gemma4-12b-glm5.2-uncensored
Building
A Gemma 4 12B student distilled from glm-5.2 — an uncensored build on Google's Gemma 4 base. Same bf16 LoRA → GGUF pipeline as the Qwen3.5 line.
adi-gemma4-*-general
Planned
A general-knowledge build, mirroring the Qwen3 line's recipe. Teacher and size TBD once a specific Gemma 4 base is picked.
A future line built on Meta's Llama 3.2 base models — the most widely-tooled student family, useful for downstream compatibility with the broader llama.cpp / Ollama ecosystem.
adi-llama3.2-*-general
Planned
A general-knowledge build on the Llama 3.2 student base, same distillation pipeline. Teacher and size TBD once a specific base is picked.
A planned line built on NVIDIA's Nemotron base — a compact, efficiency-oriented student family. The nano tier targets tiny footprints that still reason well after distillation.
adi-nemotron-3-nano-4b-glm5.2-general
Planned
First target: nemotron-3-nano:4b distilled from glm-5.2. A 4B general-knowledge student following the same bf16 LoRA → GGUF pipeline as the Qwen3.5 build.
A planned line built on Mistral's Devstral base — an agentic, code-focused student family. The first build distills a frontier teacher's reasoning into a model purpose-built for software tasks and tool use.
adi-devstral-small-2-24b-kimi2.7code-coder
Planned
First target: devstral-small-2:24b distilled from kimi-k2.7-code. A 24B agentic-coding student following the same bf16 LoRA → GGUF pipeline as the Qwen3.5 build.
A planned line built on OpenAI's gpt-oss open-weight models — a mixture-of-experts student family that brings a different architecture (and license) into the distillation lineup alongside the Qwen3 line.
adi-gpt-oss-20b-glm5.2-general
Planned
First target: a gpt-oss:20b student distilled from glm-5.2. A 20B general-knowledge build mirroring the Qwen3 line's recipe.
Each line is a student base family; within it, every model is the same base distilled from a different teacher for a different purpose. The naming scheme makes the lineage readable at a glance — adi-<base>-<size>-<teacher><purpose>.