Instructions to use disinformant/Qwen3.8-9B-Alexandria-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use disinformant/Qwen3.8-9B-Alexandria-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf disinformant/Qwen3.8-9B-Alexandria-GGUF:IQ4_XS
# Run inference directly in the terminal:
llama cli -hf disinformant/Qwen3.8-9B-Alexandria-GGUF:IQ4_XS

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf disinformant/Qwen3.8-9B-Alexandria-GGUF:IQ4_XS
# Run inference directly in the terminal:
llama cli -hf disinformant/Qwen3.8-9B-Alexandria-GGUF:IQ4_XS

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf disinformant/Qwen3.8-9B-Alexandria-GGUF:IQ4_XS
# Run inference directly in the terminal:
./llama-cli -hf disinformant/Qwen3.8-9B-Alexandria-GGUF:IQ4_XS

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf disinformant/Qwen3.8-9B-Alexandria-GGUF:IQ4_XS
# Run inference directly in the terminal:
./build/bin/llama-cli -hf disinformant/Qwen3.8-9B-Alexandria-GGUF:IQ4_XS

Use Docker

docker model run hf.co/disinformant/Qwen3.8-9B-Alexandria-GGUF:IQ4_XS

LM Studio
Jan

vLLM

How to use disinformant/Qwen3.8-9B-Alexandria-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "disinformant/Qwen3.8-9B-Alexandria-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "disinformant/Qwen3.8-9B-Alexandria-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/disinformant/Qwen3.8-9B-Alexandria-GGUF:IQ4_XS

Ollama
How to use disinformant/Qwen3.8-9B-Alexandria-GGUF with Ollama:
```
ollama run hf.co/disinformant/Qwen3.8-9B-Alexandria-GGUF:IQ4_XS
```
Unsloth Desktop

How to use disinformant/Qwen3.8-9B-Alexandria-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf disinformant/Qwen3.8-9B-Alexandria-GGUF:IQ4_XS

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "disinformant/Qwen3.8-9B-Alexandria-GGUF:IQ4_XS"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use disinformant/Qwen3.8-9B-Alexandria-GGUF with Docker Model Runner:
```
docker model run hf.co/disinformant/Qwen3.8-9B-Alexandria-GGUF:IQ4_XS
```

Lemonade

How to use disinformant/Qwen3.8-9B-Alexandria-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull disinformant/Qwen3.8-9B-Alexandria-GGUF:IQ4_XS

Run and chat with the model

lemonade run user.Qwen3.8-9B-Alexandria-GGUF-IQ4_XS

List all available models

lemonade list

Hermes Agent

How to use disinformant/Qwen3.8-9B-Alexandria-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf disinformant/Qwen3.8-9B-Alexandria-GGUF:IQ4_XS

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default disinformant/Qwen3.8-9B-Alexandria-GGUF:IQ4_XS

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use disinformant/Qwen3.8-9B-Alexandria-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf disinformant/Qwen3.8-9B-Alexandria-GGUF:IQ4_XS

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "disinformant/Qwen3.8-9B-Alexandria-GGUF:IQ4_XS" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Qwen3.8-9B-Alexandria (GGUF)

Open Science Library / Tenebras · disinformant

The Library of Alexandria was burned. What’s left is a subset. HathiTrust is frontier-scale (~19M volumes). Open Science Library is the rights-cleared slice we hold and ship. This model is a further subset.

Coverage (read this)

Layer	Status
OSL full text from Internet Archive PDFs (~1,117 books / ~682k pages)	In scope — CPT / RAG text
Images / plates / schematic crops	Untrained
Tables	Untrained as structure (crops/stubs only)

PDF origin: archive.org (ia_id per title). Not downloaded from HathiTrust. Hathi is finding-list / rights-reference only. Train JSON: disinformant/alexandria-osl-train.

Files

File	Role
`Qwen3.8-9b-Alexandria-IQ4_XS.gguf`	Phone/LAN IQ4_XS (~5.0 GB)
`mmproj-Qwen3.8-9b-Alexandria-f16.gguf`	Matching vision projector (f16) — base VL path, not OSL-image-trained

Purpose

Local, offline-first builder over cleared mid-century science/engineering text. Not a scan museum; not an official HathiTrust product.

Train your own

Public train JSON: disinformant/alexandria-osl-train — OSL/Hathi+BlendNet CPT text + Hermes FC v28 + mix recipe. Text only (images/tables untrained).

OSL packs (download with the model)

One encode → two packs (cleared volumes only):

Human: EPUB; tables/schematics as lossless image crops; optional grayscale page-PDF.
AI / RAG: compact Markdown (+ DocTags when layout matters); page text; rights + hashes; table stubs (text metadata — images not embedded in the index).

HathiTrust = finding list. Full text enters OSL only after per-edition rights clearance. Run the model with OSL text RAG.

Starting weights

petruhonk/Qwen3.8-9B-Distill-uncensored-heretic (Apache-2.0)
← empero-ai/Qwen3.8-9B-Distill
← Qwen/Qwen3.5-9B

HathiTrust

https://www.hathitrust.org/ — 19M+ items. Whole-Trust training is frontier work. OSL uses Hathi for find + provenance, then clears editions.

Citation

Qwen3.8-9B-Alexandria (OSL / Tenebras)—subset model over full OSL text holdings; images/tables untrained. Base: petruhonk ← Empero ← Qwen3.5-9B. PDFs: Internet Archive. Finding list: HathiTrust. The library was burned; what’s left is a subset.

License

Apache-2.0

Downloads last month: 602

GGUF

Model size

9B params

Architecture

qwen35

Hardware compatibility

4-bit

Model tree for disinformant/Qwen3.8-9B-Alexandria-GGUF

Base model

Qwen/Qwen3.5-9B-Base

Finetuned

Qwen/Qwen3.5-9B

Finetuned

petruhonk/Qwen3.8-9B-Distill-uncensored-heretic

Quantized

(7)

this model

disinformant
/

Qwen3.8-9B-Alexandria-GGUF

Qwen3.8-9B-Alexandria (GGUF)

Coverage (read this)

Files

Purpose

Train your own

OSL packs (download with the model)

Starting weights

HathiTrust

Citation

License

Model tree for disinformant/Qwen3.8-9B-Alexandria-GGUF

Dataset used to train disinformant/Qwen3.8-9B-Alexandria-GGUF