Instructions to use usterquant/inkling-UD-Q2_K_XL-layers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use usterquant/inkling-UD-Q2_K_XL-layers 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 usterquant/inkling-UD-Q2_K_XL-layers:BF16
# Run inference directly in the terminal:
llama cli -hf usterquant/inkling-UD-Q2_K_XL-layers:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf usterquant/inkling-UD-Q2_K_XL-layers:BF16
# Run inference directly in the terminal:
llama cli -hf usterquant/inkling-UD-Q2_K_XL-layers:BF16

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 usterquant/inkling-UD-Q2_K_XL-layers:BF16
# Run inference directly in the terminal:
./llama-cli -hf usterquant/inkling-UD-Q2_K_XL-layers:BF16

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 usterquant/inkling-UD-Q2_K_XL-layers:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf usterquant/inkling-UD-Q2_K_XL-layers:BF16

Use Docker

docker model run hf.co/usterquant/inkling-UD-Q2_K_XL-layers:BF16

LM Studio
Jan

vLLM

How to use usterquant/inkling-UD-Q2_K_XL-layers with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "usterquant/inkling-UD-Q2_K_XL-layers"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "usterquant/inkling-UD-Q2_K_XL-layers",
		"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/usterquant/inkling-UD-Q2_K_XL-layers:BF16

Ollama
How to use usterquant/inkling-UD-Q2_K_XL-layers with Ollama:
```
ollama run hf.co/usterquant/inkling-UD-Q2_K_XL-layers:BF16
```

Unsloth Studio

How to use usterquant/inkling-UD-Q2_K_XL-layers with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for usterquant/inkling-UD-Q2_K_XL-layers to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for usterquant/inkling-UD-Q2_K_XL-layers to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for usterquant/inkling-UD-Q2_K_XL-layers to start chatting

How to use usterquant/inkling-UD-Q2_K_XL-layers with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf usterquant/inkling-UD-Q2_K_XL-layers:BF16

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "usterquant/inkling-UD-Q2_K_XL-layers:BF16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use usterquant/inkling-UD-Q2_K_XL-layers with Docker Model Runner:
```
docker model run hf.co/usterquant/inkling-UD-Q2_K_XL-layers:BF16
```

Lemonade

How to use usterquant/inkling-UD-Q2_K_XL-layers with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull usterquant/inkling-UD-Q2_K_XL-layers:BF16

Run and chat with the model

lemonade run user.inkling-UD-Q2_K_XL-layers-BF16

List all available models

lemonade list

Hermes Agent

How to use usterquant/inkling-UD-Q2_K_XL-layers with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf usterquant/inkling-UD-Q2_K_XL-layers:BF16

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 usterquant/inkling-UD-Q2_K_XL-layers:BF16

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use usterquant/inkling-UD-Q2_K_XL-layers with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf usterquant/inkling-UD-Q2_K_XL-layers:BF16

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 "usterquant/inkling-UD-Q2_K_XL-layers:BF16" \
  --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"

inkling-UD-Q2_K_XL-layers / README.md

usterquant

Duplicate from meshllm/inkling-UD-Q2_K_XL-layers

31639eb 16 days ago

preview code

Raw

History Blame

5.85 kB

	---
	library_name: mesh-llm
	base_model:
	- "unsloth/inkling-GGUF"
	pipeline_tag: "image-text-to-text"
	tags:
	- gguf
	- mesh-llm
	- layer-package
	- skippy
	- distributed-inference
	- local-inference
	- openai-compatible
	- experimental
	---

	<div align="center">
	<a href="https://www.meshllm.cloud">
	<img src="https://meshllm.cloud/assets/images/jelly-logo-wordmark.png" alt="Mesh LLM" width="220">
	</a>

	<h1>inkling-UD-Q2_K_XL</h1>

	<p>
	<strong>Distributed GGUF inference package for Mesh LLM</strong>
	</p>

	<p>
	<a href="https://www.meshllm.cloud"><img alt="Website" src="https://img.shields.io/badge/Website-meshllm.cloud-111111?style=for-the-badge"></a>
	<a href="https://github.com/Mesh-LLM/mesh-llm"><img alt="GitHub" src="https://img.shields.io/badge/GitHub-Mesh--LLM-24292f?style=for-the-badge&logo=github"></a>
	<a href="https://discord.gg/rs6fmc63eN"><img alt="Discord" src="https://img.shields.io/badge/Discord-Join-5865F2?style=for-the-badge&logo=discord&logoColor=white"></a>
	</p>
	</div>

	> [!WARNING]
	> Experimental package: artifact integrity may be validated, but runtime, split-correctness, and multimodal certification are still pending. This package is not discoverable through `meshllm/catalog@main` until its Hugging Face catalog PR is reviewed and merged.

	GGUF layer package for running inkling-UD-Q2_K_XL across a local Mesh LLM cluster.

	This package is derived from [unsloth/inkling-GGUF](https://huggingface.co/unsloth/inkling-GGUF) and keeps the original GGUF distribution split into per-layer artifacts for distributed inference.

	## Highlights

	\| Run locally \| Pool multiple machines \| OpenAI-compatible \| Package variant \|
	\|---\|---\|---\|---\|
	\| Private inference on your hardware \| Split layers across peers \| Serve `/v1/chat/completions` locally \| `UD-Q2_K_XL` layer package \|

	## Model Overview

	\| Property \| Value \|
	\|---\|---\|
	\| Source model \| [unsloth/inkling-GGUF](https://huggingface.co/unsloth/inkling-GGUF) \|
	\| Model id \| `unsloth/inkling-GGUF:UD-Q2_K_XL` \|
	\| Family \| inkling \|
	\| Parameter scale \| not recorded \|
	\| Quantization \| `UD-Q2_K_XL` \|
	\| Layer count \| 66 \|
	\| Activation width \| 6144 \|
	\| Package size \| 296.5 GB \|
	\| Source file \| `UD-Q2_K_XL/inkling-UD-Q2_K_XL-00001-of-00008.gguf` \|
	\| Package repo \| [meshllm/inkling-UD-Q2_K_XL-layers](https://huggingface.co/meshllm/inkling-UD-Q2_K_XL-layers) \|

	## Recommended Use

	- Local and private inference with Mesh LLM.
	- Multi-machine serving when the full GGUF is too large for one host.
	- OpenAI-compatible chat/completions workflows through Mesh LLM's local API.

	For upstream architecture details, chat template guidance, sampling recommendations, license terms, and benchmark notes, see the source model card: [unsloth/inkling-GGUF](https://huggingface.co/unsloth/inkling-GGUF).

	## Quickstart

	```bash
	# Run this on each machine that should contribute memory/compute.
	mesh-llm serve --model "meshllm/inkling-UD-Q2_K_XL-layers" --split
	```

	```bash
	# Check the mesh and discover the OpenAI-compatible model name.
	curl -s http://localhost:3131/api/status
	curl -s http://localhost:3131/v1/models
	```

	```bash
	# Send an OpenAI-compatible chat request.
	curl -s http://localhost:3131/v1/chat/completions \
	-H "Content-Type: application/json" \
	-d '{
	"model": "unsloth/inkling-GGUF:UD-Q2_K_XL",
	"messages": [{"role": "user", "content": "Write a tiny hello-world function in Rust."}],
	"max_tokens": 128
	}'
	```

	## Package Variant

	\| Property \| Value \|
	\|---\|---\|
	\| Format \| `layer-package` \|
	\| Canonical source ref \| `unsloth/inkling-GGUF@d3e9ffca48751dbe8b59dab5cfa364621257c682/UD-Q2_K_XL/inkling-UD-Q2_K_XL-00001-of-00008.gguf` \|
	\| Source revision \| `d3e9ffca48751dbe8b59dab5cfa364621257c682` \|
	\| Source SHA-256 \| `8b153eb6a470303f227ef2ba5b515e4e53cc51be65f4395490aa6e37f377bebf` \|
	\| Skippy ABI \| `0.1.30` \|
	\| Package manifest SHA-256 \| `6cda4ce683e8046818d0d51c57e00b61d2245c36ba7b21a4fb7c51ab82c039b7` \|

	## What Is Included

	\| Artifact \| Path \| Contents \| SHA-256 \|
	\|---\|---\|---\|---\|
	\| Manifest \| `model-package.json` \| Package schema, source identity, checksums \| `6cda4ce683e8046818d0d51c57e00b61d2245c36ba7b21a4fb7c51ab82c039b7` \|
	\| Metadata \| `shared/metadata.gguf` \| 1 tensors, 12.4 MB \| `c2332ae2f8fc2a711861bae5c96720592aee75cdf7868a3bade02bc513f03bf5` \|
	\| Embeddings \| `shared/embeddings.gguf` \| 2 tensors, 822.2 MB \| `2021ca206c89e66637e4e048caea5c5b181413ce4e9b045fb6aff8db315f7a7a` \|
	\| Output head \| `shared/output.gguf` \| 3 tensors, 675.0 MB \| `0ca256c69c9c311dfb5671643f9edaff62de8706453a68aa34b953aaac6f8b21` \|
	\| Transformer layers \| `layers/layer-*.gguf` \| 66 layer artifacts, 1574 tensors, 294.9 GB \| `see model-package.json` \|
	\| Projector \| `projectors/mmproj-BF16.gguf` \| mmproj projector, 174.8 MB \| `662c925e1df293cfba16ffd6bd53dac31d3c73160ba65dff7270d7a70f351e91` \|

	## Validation

	Generated by the Mesh LLM HF Jobs splitter from `mesh-llm` ref `codex/inkling-q2-skippy`.
	Each artifact is checksummed as it is written, uploaded to this repository, and removed from the job workspace before the next artifact is produced.

	```bash
	skippy-model-package write-package "/source/UD-Q2_K_XL/inkling-UD-Q2_K_XL-00001-of-00008.gguf" --out-dir "/tmp/meshllm-layer-job-meshllm_inkling-UD-Q2_K_XL-layers-193/package"
	```

	## Links

	- Source model: [unsloth/inkling-GGUF](https://huggingface.co/unsloth/inkling-GGUF)
	- Mesh LLM website: [meshllm.cloud](https://www.meshllm.cloud)
	- Mesh LLM: [github.com/Mesh-LLM/mesh-llm](https://github.com/Mesh-LLM/mesh-llm)
	- Discord: [discord.gg/rs6fmc63eN](https://discord.gg/rs6fmc63eN)
	- Package catalog: [meshllm/catalog](https://huggingface.co/datasets/meshllm/catalog)
	- Package format: [layer-package-repos.md](https://github.com/Mesh-LLM/mesh-llm/blob/main/docs/specs/layer-package-repos.md)