Instructions to use mradermacher/SpaceThinker-Qwen2.5VL-3B-i1-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mradermacher/SpaceThinker-Qwen2.5VL-3B-i1-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("mradermacher/SpaceThinker-Qwen2.5VL-3B-i1-GGUF", dtype="auto")

llama-cpp-python

How to use mradermacher/SpaceThinker-Qwen2.5VL-3B-i1-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="mradermacher/SpaceThinker-Qwen2.5VL-3B-i1-GGUF",
	filename="SpaceThinker-Qwen2.5VL-3B.i1-IQ1_M.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use mradermacher/SpaceThinker-Qwen2.5VL-3B-i1-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf mradermacher/SpaceThinker-Qwen2.5VL-3B-i1-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf mradermacher/SpaceThinker-Qwen2.5VL-3B-i1-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf mradermacher/SpaceThinker-Qwen2.5VL-3B-i1-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf mradermacher/SpaceThinker-Qwen2.5VL-3B-i1-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 mradermacher/SpaceThinker-Qwen2.5VL-3B-i1-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf mradermacher/SpaceThinker-Qwen2.5VL-3B-i1-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 mradermacher/SpaceThinker-Qwen2.5VL-3B-i1-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf mradermacher/SpaceThinker-Qwen2.5VL-3B-i1-GGUF:Q4_K_M

Use Docker

docker model run hf.co/mradermacher/SpaceThinker-Qwen2.5VL-3B-i1-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use mradermacher/SpaceThinker-Qwen2.5VL-3B-i1-GGUF with Ollama:
```
ollama run hf.co/mradermacher/SpaceThinker-Qwen2.5VL-3B-i1-GGUF:Q4_K_M
```

Unsloth Studio new

How to use mradermacher/SpaceThinker-Qwen2.5VL-3B-i1-GGUF 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 mradermacher/SpaceThinker-Qwen2.5VL-3B-i1-GGUF 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 mradermacher/SpaceThinker-Qwen2.5VL-3B-i1-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for mradermacher/SpaceThinker-Qwen2.5VL-3B-i1-GGUF to start chatting

Pi new

How to use mradermacher/SpaceThinker-Qwen2.5VL-3B-i1-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf mradermacher/SpaceThinker-Qwen2.5VL-3B-i1-GGUF:Q4_K_M

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": "mradermacher/SpaceThinker-Qwen2.5VL-3B-i1-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use mradermacher/SpaceThinker-Qwen2.5VL-3B-i1-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf mradermacher/SpaceThinker-Qwen2.5VL-3B-i1-GGUF:Q4_K_M

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 mradermacher/SpaceThinker-Qwen2.5VL-3B-i1-GGUF:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use mradermacher/SpaceThinker-Qwen2.5VL-3B-i1-GGUF with Docker Model Runner:
```
docker model run hf.co/mradermacher/SpaceThinker-Qwen2.5VL-3B-i1-GGUF:Q4_K_M
```

Lemonade

How to use mradermacher/SpaceThinker-Qwen2.5VL-3B-i1-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mradermacher/SpaceThinker-Qwen2.5VL-3B-i1-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.SpaceThinker-Qwen2.5VL-3B-i1-GGUF-Q4_K_M

List all available models

lemonade list

SpaceThinker-Qwen2.5VL-3B-i1-GGUF / README.md

mradermacher

auto-patch README.md

07f17a6 verified 11 months ago

preview code

raw

history blame contribute delete

6.53 kB

	---
	base_model: remyxai/SpaceThinker-Qwen2.5VL-3B
	datasets:
	- remyxai/SpaceThinker
	language:
	- en
	library_name: transformers
	license: apache-2.0
	license_link: https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct/blob/main/LICENSE
	license_name: qwen-research
	mradermacher:
	readme_rev: 1
	quantized_by: mradermacher
	tags:
	- remyx
	- qwen2.5-vl
	- spatial-reasoning
	- multimodal
	- vlm
	- vqasynth
	- thinking
	- reasoning
	- test-time-compute
	- robotics
	- embodied-ai
	- quantitative-spatial-reasoning
	- distance-estimation
	- visual-question-answering
	---
	## About

	<!-- ### quantize_version: 2 -->
	<!-- ### output_tensor_quantised: 1 -->
	<!-- ### convert_type: hf -->
	<!-- ### vocab_type: -->
	<!-- ### tags: nicoboss -->
	weighted/imatrix quants of https://huggingface.co/remyxai/SpaceThinker-Qwen2.5VL-3B

	<!-- provided-files -->

	*For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#SpaceThinker-Qwen2.5VL-3B-i1-GGUF).*

	static quants are available at https://huggingface.co/mradermacher/SpaceThinker-Qwen2.5VL-3B-GGUF

	This is a vision model - mmproj files (if any) will be in the [static repository](https://huggingface.co/mradermacher/SpaceThinker-Qwen2.5VL-3B-GGUF).
	## Usage

	If you are unsure how to use GGUF files, refer to one of [TheBloke's
	READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
	more details, including on how to concatenate multi-part files.

	## Provided Quants

	(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)

	\| Link \| Type \| Size/GB \| Notes \|
	\|:-----\|:-----\|--------:\|:------\|
	\| [GGUF](https://huggingface.co/mradermacher/SpaceThinker-Qwen2.5VL-3B-i1-GGUF/resolve/main/SpaceThinker-Qwen2.5VL-3B.i1-IQ1_S.gguf) \| i1-IQ1_S \| 0.9 \| for the desperate \|
	\| [GGUF](https://huggingface.co/mradermacher/SpaceThinker-Qwen2.5VL-3B-i1-GGUF/resolve/main/SpaceThinker-Qwen2.5VL-3B.i1-IQ1_M.gguf) \| i1-IQ1_M \| 1.0 \| mostly desperate \|
	\| [GGUF](https://huggingface.co/mradermacher/SpaceThinker-Qwen2.5VL-3B-i1-GGUF/resolve/main/SpaceThinker-Qwen2.5VL-3B.i1-IQ2_XXS.gguf) \| i1-IQ2_XXS \| 1.0 \| \|
	\| [GGUF](https://huggingface.co/mradermacher/SpaceThinker-Qwen2.5VL-3B-i1-GGUF/resolve/main/SpaceThinker-Qwen2.5VL-3B.i1-IQ2_XS.gguf) \| i1-IQ2_XS \| 1.1 \| \|
	\| [GGUF](https://huggingface.co/mradermacher/SpaceThinker-Qwen2.5VL-3B-i1-GGUF/resolve/main/SpaceThinker-Qwen2.5VL-3B.i1-IQ2_S.gguf) \| i1-IQ2_S \| 1.2 \| \|
	\| [GGUF](https://huggingface.co/mradermacher/SpaceThinker-Qwen2.5VL-3B-i1-GGUF/resolve/main/SpaceThinker-Qwen2.5VL-3B.i1-IQ2_M.gguf) \| i1-IQ2_M \| 1.2 \| \|
	\| [GGUF](https://huggingface.co/mradermacher/SpaceThinker-Qwen2.5VL-3B-i1-GGUF/resolve/main/SpaceThinker-Qwen2.5VL-3B.i1-Q2_K_S.gguf) \| i1-Q2_K_S \| 1.3 \| very low quality \|
	\| [GGUF](https://huggingface.co/mradermacher/SpaceThinker-Qwen2.5VL-3B-i1-GGUF/resolve/main/SpaceThinker-Qwen2.5VL-3B.i1-Q2_K.gguf) \| i1-Q2_K \| 1.4 \| IQ3_XXS probably better \|
	\| [GGUF](https://huggingface.co/mradermacher/SpaceThinker-Qwen2.5VL-3B-i1-GGUF/resolve/main/SpaceThinker-Qwen2.5VL-3B.i1-IQ3_XXS.gguf) \| i1-IQ3_XXS \| 1.4 \| lower quality \|
	\| [GGUF](https://huggingface.co/mradermacher/SpaceThinker-Qwen2.5VL-3B-i1-GGUF/resolve/main/SpaceThinker-Qwen2.5VL-3B.i1-IQ3_XS.gguf) \| i1-IQ3_XS \| 1.5 \| \|
	\| [GGUF](https://huggingface.co/mradermacher/SpaceThinker-Qwen2.5VL-3B-i1-GGUF/resolve/main/SpaceThinker-Qwen2.5VL-3B.i1-Q3_K_S.gguf) \| i1-Q3_K_S \| 1.6 \| IQ3_XS probably better \|
	\| [GGUF](https://huggingface.co/mradermacher/SpaceThinker-Qwen2.5VL-3B-i1-GGUF/resolve/main/SpaceThinker-Qwen2.5VL-3B.i1-IQ3_S.gguf) \| i1-IQ3_S \| 1.6 \| beats Q3_K* \|
	\| [GGUF](https://huggingface.co/mradermacher/SpaceThinker-Qwen2.5VL-3B-i1-GGUF/resolve/main/SpaceThinker-Qwen2.5VL-3B.i1-IQ3_M.gguf) \| i1-IQ3_M \| 1.6 \| \|
	\| [GGUF](https://huggingface.co/mradermacher/SpaceThinker-Qwen2.5VL-3B-i1-GGUF/resolve/main/SpaceThinker-Qwen2.5VL-3B.i1-Q3_K_M.gguf) \| i1-Q3_K_M \| 1.7 \| IQ3_S probably better \|
	\| [GGUF](https://huggingface.co/mradermacher/SpaceThinker-Qwen2.5VL-3B-i1-GGUF/resolve/main/SpaceThinker-Qwen2.5VL-3B.i1-Q3_K_L.gguf) \| i1-Q3_K_L \| 1.8 \| IQ3_M probably better \|
	\| [GGUF](https://huggingface.co/mradermacher/SpaceThinker-Qwen2.5VL-3B-i1-GGUF/resolve/main/SpaceThinker-Qwen2.5VL-3B.i1-IQ4_XS.gguf) \| i1-IQ4_XS \| 1.8 \| \|
	\| [GGUF](https://huggingface.co/mradermacher/SpaceThinker-Qwen2.5VL-3B-i1-GGUF/resolve/main/SpaceThinker-Qwen2.5VL-3B.i1-IQ4_NL.gguf) \| i1-IQ4_NL \| 1.9 \| prefer IQ4_XS \|
	\| [GGUF](https://huggingface.co/mradermacher/SpaceThinker-Qwen2.5VL-3B-i1-GGUF/resolve/main/SpaceThinker-Qwen2.5VL-3B.i1-Q4_0.gguf) \| i1-Q4_0 \| 1.9 \| fast, low quality \|
	\| [GGUF](https://huggingface.co/mradermacher/SpaceThinker-Qwen2.5VL-3B-i1-GGUF/resolve/main/SpaceThinker-Qwen2.5VL-3B.i1-Q4_K_S.gguf) \| i1-Q4_K_S \| 1.9 \| optimal size/speed/quality \|
	\| [GGUF](https://huggingface.co/mradermacher/SpaceThinker-Qwen2.5VL-3B-i1-GGUF/resolve/main/SpaceThinker-Qwen2.5VL-3B.i1-Q4_K_M.gguf) \| i1-Q4_K_M \| 2.0 \| fast, recommended \|
	\| [GGUF](https://huggingface.co/mradermacher/SpaceThinker-Qwen2.5VL-3B-i1-GGUF/resolve/main/SpaceThinker-Qwen2.5VL-3B.i1-Q4_1.gguf) \| i1-Q4_1 \| 2.1 \| \|
	\| [GGUF](https://huggingface.co/mradermacher/SpaceThinker-Qwen2.5VL-3B-i1-GGUF/resolve/main/SpaceThinker-Qwen2.5VL-3B.i1-Q5_K_S.gguf) \| i1-Q5_K_S \| 2.3 \| \|
	\| [GGUF](https://huggingface.co/mradermacher/SpaceThinker-Qwen2.5VL-3B-i1-GGUF/resolve/main/SpaceThinker-Qwen2.5VL-3B.i1-Q5_K_M.gguf) \| i1-Q5_K_M \| 2.3 \| \|
	\| [GGUF](https://huggingface.co/mradermacher/SpaceThinker-Qwen2.5VL-3B-i1-GGUF/resolve/main/SpaceThinker-Qwen2.5VL-3B.i1-Q6_K.gguf) \| i1-Q6_K \| 2.6 \| practically like static Q6_K \|

	Here is a handy graph by ikawrakow comparing some lower-quality quant
	types (lower is better):

	![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)

	And here are Artefact2's thoughts on the matter:
	https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9

	## FAQ / Model Request

	See https://huggingface.co/mradermacher/model_requests for some answers to
	questions you might have and/or if you want some other model quantized.

	## Thanks

	I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
	me use its servers and providing upgrades to my workstation to enable
	this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.

	<!-- end -->