Instructions to use forkjoin-ai/qwen2.5-vl-3b-instruct-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 forkjoin-ai/qwen2.5-vl-3b-instruct-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 forkjoin-ai/qwen2.5-vl-3b-instruct-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf forkjoin-ai/qwen2.5-vl-3b-instruct-gguf:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf forkjoin-ai/qwen2.5-vl-3b-instruct-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf forkjoin-ai/qwen2.5-vl-3b-instruct-gguf:Q4_K_M

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 forkjoin-ai/qwen2.5-vl-3b-instruct-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf forkjoin-ai/qwen2.5-vl-3b-instruct-gguf:Q4_K_M

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 forkjoin-ai/qwen2.5-vl-3b-instruct-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf forkjoin-ai/qwen2.5-vl-3b-instruct-gguf:Q4_K_M

Use Docker

docker model run hf.co/forkjoin-ai/qwen2.5-vl-3b-instruct-gguf:Q4_K_M

LM Studio
Jan

vLLM

How to use forkjoin-ai/qwen2.5-vl-3b-instruct-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "forkjoin-ai/qwen2.5-vl-3b-instruct-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": "forkjoin-ai/qwen2.5-vl-3b-instruct-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/forkjoin-ai/qwen2.5-vl-3b-instruct-gguf:Q4_K_M

Ollama
How to use forkjoin-ai/qwen2.5-vl-3b-instruct-gguf with Ollama:
```
ollama run hf.co/forkjoin-ai/qwen2.5-vl-3b-instruct-gguf:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use forkjoin-ai/qwen2.5-vl-3b-instruct-gguf with Docker Model Runner:
```
docker model run hf.co/forkjoin-ai/qwen2.5-vl-3b-instruct-gguf:Q4_K_M
```

Lemonade

How to use forkjoin-ai/qwen2.5-vl-3b-instruct-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull forkjoin-ai/qwen2.5-vl-3b-instruct-gguf:Q4_K_M

Run and chat with the model

lemonade run user.qwen2.5-vl-3b-instruct-gguf-Q4_K_M

List all available models

lemonade list

Atomic Chat

qwen2.5-vl-3b-instruct-gguf / README.md

buley

Fix model card accuracy (format/filename)

8553662 verified 3 months ago

preview code

Raw

History Blame Contribute Delete

3.43 kB

	---
	language:
	- en
	license: apache-2.0
	library_name: gguf
	tags:
	- gguf
	- qwen2
	- instruct
	- vision
	- multimodal
	- affectively
	- edgework
	- aether
	- distributed-inference
	- edge-deployment
	base_model: Qwen/Qwen2.5-VL-3B-Instruct
	base_model_relation: quantized
	pipeline_tag: image-text-to-text
	---

	# Qwen2.5 VL 3b Instruct (GGUF, Q4_K_M)

	> Production-ready GGUF quantization of [Qwen/Qwen2.5-VL-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct) for distributed visual understanding and reasoning — powered by the [Aether](https://github.com/forkjoin-ai/aether) edge inference runtime on [Edgework.ai](https://edgework.ai).

	## Model Details

	\| Property \| Value \|
	\|----------\|-------\|
	\| Base model \| [Qwen/Qwen2.5-VL-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct) \|
	\| Parameters \| 3B \|
	\| Architecture \| Qwen2 \|
	\| Quantization \| Q4_K_M \|
	\| Format \| GGUF \|
	\| Size \| ~1.8 GB \|
	\| License \| apache-2.0 \|

	## Usage

	### With llama.cpp

	```bash
	./llama-cli -m Qwen2.5-VL-3B-Instruct-Q4_K_M.gguf -p "Your prompt here" -n 256
	```

	### With Aether (Distributed Inference)

	This model is deployed across the [Aether](https://github.com/forkjoin-ai/aether) distributed inference network. Weights are layer-sharded and distributed across multiple edge nodes for parallel inference.

	## Also available: `.knot` (sovereign format)

	This repo ships [`qwen2.5-vl-3b.knot`](./qwen2.5-vl-3b.knot) — the model weights in the KNOT container that the [Aether](https://github.com/forkjoin-ai/aether) distributed-inference runtime loads natively (the GGUF, when present, sits right beside it). A KNOT is a single self-describing file with a JSON table-of-contents, so any single tensor is one HTTP `Range` request — ideal for streaming weights to edge nodes.

	\| \| GGUF \| KNOT \|
	\|---\|---\|---\|
	\| Container \| format-specific header \| single file, JSON table-of-contents \|
	\| Per-tensor fetch \| whole-file oriented \| one tensor = one Range request \|
	\| Ecosystem \| broad (llama.cpp, …) \| Aether / Gnosis runtime \|

	```bash
	huggingface-cli download forkjoin-ai/qwen2.5-vl-3b-instruct-gguf qwen2.5-vl-3b.knot --local-dir ./knots
	```

	Full format spec: [KNOT_FORMAT.md](https://github.com/forkjoin-ai/aether/blob/main/docs/model-cards/KNOT_FORMAT.md). Inspect the header with `bun run open-source/bitwise/scripts/dump-knot.ts qwen2.5-vl-3b.knot`.

	## Deployment Architecture

	This model runs on the Aether distributed inference runtime — a custom engine that shards model layers across multiple nodes for parallel execution:

	1. Coordinator receives requests and manages token generation
	2. Layer nodes each hold a subset of model layers (2 nodes for this model)
	3. Hidden states flow between nodes via gRPC
	4. Zero cold start via warm pool scheduling

	Deployed via [Edgework.ai](https://edgework.ai) — bringing fast, cheap, and private inference as close to the user as possible.

	## About

	Published by [AFFECTIVELY](https://huggingface.co/forkjoin-ai) · Managed by [@buley](https://huggingface.co/buley)

	We quantize and publish production-ready models for distributed edge inference via the [Aether](https://github.com/forkjoin-ai/aether) runtime. Every release is tested for correctness and stability before publication.

	- [All models](https://huggingface.co/forkjoin-ai) · [GitHub](https://github.com/forkjoin-ai) · [Edgework.ai](https://edgework.ai)