CoolFace
Modelpublic

NGARiAI/qwen3.8-27B

sourceHugging Faceapache-2.0updated 21d agoView on Hugging Face
1likes
Model Card

NGARi Sovereign Edge — Qwen 27B Serving Configuration

This repository contains the serving configuration and model card for running a Qwen 27B-class instruct model (Qwen3.5 family, 27.3B params, Q4KM GGUF) on NGARi Orin 64GB edge hardware via Ollama — with zero cloud dependency and a verified air-gap.

This repo ships configuration (Modelfile + card), not weights. Weights are pulled through Ollama's registry under the tag qwen3.8:27b.

The role of this model in the NGARi stack

The 27B model is NGARi's R&D engine, not just an end product. It powers the creation of NGARi's small, fast edge models:

UseWhat the 27B doesOutput
Knowledge distillationGenerates reasoning traces / logits as a teacherSmarter 1.5B students (e.g. ngari-ft-distilled)
Synthetic dataCreates diverse, high-fidelity training examplesngari-datasets
Tool-use trainingSimulates tool schemas, queries, correct callsngari-tool (100% tool-format eval)
LLM-as-a-judgeScores student outputs for DPO/preference tuningAligned small models, fewer hallucinations
Sovereign specializationMasters private/local data in a secure environment, then distillsCustom edge models that preserve privacy

The result is the "holy trinity" of edge deployment: accurate (teacher distillation), powerful (specialized tool use), fast (small parameter count).

Key features

  • —Runs on NVIDIA Jetson AGX Orin 64GB (aarch64) — Q4KM, ~16GB footprint
  • —262K-token context window; completion, tools, thinking, vision capabilities
  • —Zero cloud dependency for inference; verified air-gap (monitored via /proc/net/dev)
  • —Apache 2.0 kernel: github.com/NGARiAI/ns-bos-kernel

Usage (Ollama)

bash
ollama run qwen3.8:27b "your prompt here"
# long-lived sessions:
ollama run qwen3.8:27b --keepalive 20m "your prompt"

Licensing

  • —Qwen base model: Apache 2.0 (Qwen license terms apply to the weights)
  • —NGARi-authored configuration and pipeline artifacts: Apache 2.0 — Bison Venture Partners LLC dba NGARI

Sovereign AI

All inference runs on user-owned edge hardware. Zero cloud dependency. Verified air-gap. "AI You Own. Completely."