Instructions to use tensorblock/QwQ-Math-IO-500M-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tensorblock/QwQ-Math-IO-500M-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="tensorblock/QwQ-Math-IO-500M-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("tensorblock/QwQ-Math-IO-500M-GGUF", dtype="auto")

llama-cpp-python

How to use tensorblock/QwQ-Math-IO-500M-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="tensorblock/QwQ-Math-IO-500M-GGUF",
	filename="QwQ-Math-IO-500M-Q2_K.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use tensorblock/QwQ-Math-IO-500M-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf tensorblock/QwQ-Math-IO-500M-GGUF:Q2_K
# Run inference directly in the terminal:
llama-cli -hf tensorblock/QwQ-Math-IO-500M-GGUF:Q2_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf tensorblock/QwQ-Math-IO-500M-GGUF:Q2_K
# Run inference directly in the terminal:
llama-cli -hf tensorblock/QwQ-Math-IO-500M-GGUF:Q2_K

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 tensorblock/QwQ-Math-IO-500M-GGUF:Q2_K
# Run inference directly in the terminal:
./llama-cli -hf tensorblock/QwQ-Math-IO-500M-GGUF:Q2_K

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 tensorblock/QwQ-Math-IO-500M-GGUF:Q2_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf tensorblock/QwQ-Math-IO-500M-GGUF:Q2_K

Use Docker

docker model run hf.co/tensorblock/QwQ-Math-IO-500M-GGUF:Q2_K

LM Studio
Jan

vLLM

How to use tensorblock/QwQ-Math-IO-500M-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tensorblock/QwQ-Math-IO-500M-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": "tensorblock/QwQ-Math-IO-500M-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tensorblock/QwQ-Math-IO-500M-GGUF:Q2_K

SGLang

How to use tensorblock/QwQ-Math-IO-500M-GGUF with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "tensorblock/QwQ-Math-IO-500M-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tensorblock/QwQ-Math-IO-500M-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "tensorblock/QwQ-Math-IO-500M-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tensorblock/QwQ-Math-IO-500M-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use tensorblock/QwQ-Math-IO-500M-GGUF with Ollama:
```
ollama run hf.co/tensorblock/QwQ-Math-IO-500M-GGUF:Q2_K
```

Unsloth Studio new

How to use tensorblock/QwQ-Math-IO-500M-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 tensorblock/QwQ-Math-IO-500M-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 tensorblock/QwQ-Math-IO-500M-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for tensorblock/QwQ-Math-IO-500M-GGUF to start chatting

Pi new

How to use tensorblock/QwQ-Math-IO-500M-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf tensorblock/QwQ-Math-IO-500M-GGUF:Q2_K

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": "tensorblock/QwQ-Math-IO-500M-GGUF:Q2_K"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use tensorblock/QwQ-Math-IO-500M-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 tensorblock/QwQ-Math-IO-500M-GGUF:Q2_K

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 tensorblock/QwQ-Math-IO-500M-GGUF:Q2_K

Run Hermes

hermes

Docker Model Runner
How to use tensorblock/QwQ-Math-IO-500M-GGUF with Docker Model Runner:
```
docker model run hf.co/tensorblock/QwQ-Math-IO-500M-GGUF:Q2_K
```

Lemonade

How to use tensorblock/QwQ-Math-IO-500M-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull tensorblock/QwQ-Math-IO-500M-GGUF:Q2_K

Run and chat with the model

lemonade run user.QwQ-Math-IO-500M-GGUF-Q2_K

List all available models

lemonade list

morriszms commited on Mar 7, 2025

Commit

e5ae04f

verified ·

1 Parent(s): 477513a

Upload folder using huggingface_hub

Browse files

Files changed (14) hide show

.gitattributes +12 -0
QwQ-Math-IO-500M-Q2_K.gguf +3 -0
QwQ-Math-IO-500M-Q3_K_L.gguf +3 -0
QwQ-Math-IO-500M-Q3_K_M.gguf +3 -0
QwQ-Math-IO-500M-Q3_K_S.gguf +3 -0
QwQ-Math-IO-500M-Q4_0.gguf +3 -0
QwQ-Math-IO-500M-Q4_K_M.gguf +3 -0
QwQ-Math-IO-500M-Q4_K_S.gguf +3 -0
QwQ-Math-IO-500M-Q5_0.gguf +3 -0
QwQ-Math-IO-500M-Q5_K_M.gguf +3 -0
QwQ-Math-IO-500M-Q5_K_S.gguf +3 -0
QwQ-Math-IO-500M-Q6_K.gguf +3 -0
QwQ-Math-IO-500M-Q8_0.gguf +3 -0
README.md +86 -0

.gitattributes CHANGED Viewed

@@ -33,3 +33,15 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+QwQ-Math-IO-500M-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+QwQ-Math-IO-500M-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+QwQ-Math-IO-500M-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+QwQ-Math-IO-500M-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+QwQ-Math-IO-500M-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+QwQ-Math-IO-500M-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+QwQ-Math-IO-500M-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+QwQ-Math-IO-500M-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+QwQ-Math-IO-500M-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+QwQ-Math-IO-500M-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+QwQ-Math-IO-500M-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+QwQ-Math-IO-500M-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

QwQ-Math-IO-500M-Q2_K.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:9a2d298215a605baf7ac01380eadcec7fb52172d987f0f0b90ff2703413c703b
+size 338607328

QwQ-Math-IO-500M-Q3_K_L.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:a7e5bba8ae47b5175ba7e3650df88d061852372dcdba20ebcb635f455719d490
+size 369358048

QwQ-Math-IO-500M-Q3_K_M.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:5e9db7d9c80b0594a22787dd55b9f5897147cb20c3507e052c7a704e252194b5
+size 355466464

QwQ-Math-IO-500M-Q3_K_S.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:851a2be8b403d68fcff86b7347d5f211ffde38792958b02ae52d3f513e205dd2
+size 338263264

QwQ-Math-IO-500M-Q4_0.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:4ebc43b5ccbac60238a834063be6ad0c05ff39f9de634b47430bdc25c06f3284
+size 352154848

QwQ-Math-IO-500M-Q4_K_M.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:fff1fbcf3e673f6fc7883cb029eebf256e4554a3ba0450cfb962a2882c8404b0
+size 397807840

QwQ-Math-IO-500M-Q4_K_S.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:4d07d397263864697a806eb281df309b4c5638cb00f82370a0707f6722de2ec0
+size 385471712

QwQ-Math-IO-500M-Q5_0.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:99e2cac0fc1b15fe7a8910e5b60496437cb7745aa2e351aa7567d08aaef1aed1
+size 396883168

QwQ-Math-IO-500M-Q5_K_M.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:5e36a4dfffa5525e98673fa0b91e6591ec1df75d75ffcd8a22d7a3bdfc4af10e
+size 420085984

QwQ-Math-IO-500M-Q5_K_S.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:7d6084303a648130dc1e5707ae6358cd3f79d7f460139a46c752f47197c9ce52
+size 412710112

QwQ-Math-IO-500M-Q6_K.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:32d651e8e6c2732509c9da0d1c71bbb90ba148cdd62477703bbbb5d5220201e0
+size 505736416

QwQ-Math-IO-500M-Q8_0.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:f0d5a0b969550bb8279303d771cfd4940cf28af826880525f513f7154cd67aa5
+size 531068128

README.md ADDED Viewed

	@@ -0,0 +1,86 @@

+---
+license: apache-2.0
+language:
+- en
+base_model: prithivMLmods/QwQ-Math-IO-500M
+pipeline_tag: text-generation
+library_name: transformers
+tags:
+- qwq
+- reasoning
+- TensorBlock
+- GGUF
+---
+<div style="width: auto; margin-left: auto; margin-right: auto">
+<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
+</div>
+<div style="display: flex; justify-content: space-between; width: 100%;">
+    <div style="display: flex; flex-direction: column; align-items: flex-start;">
+        <p style="margin-top: 0.5em; margin-bottom: 0em;">
+            Feedback and support: TensorBlock's  <a href="https://x.com/tensorblock_aoi">Twitter/X</a>, <a href="https://t.me/TensorBlock">Telegram Group</a> and <a href="https://x.com/tensorblock_aoi">Discord server</a>
+        </p>
+    </div>
+</div>
+## prithivMLmods/QwQ-Math-IO-500M - GGUF
+This repo contains GGUF format model files for [prithivMLmods/QwQ-Math-IO-500M](https://huggingface.co/prithivMLmods/QwQ-Math-IO-500M).
+The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4823](https://github.com/ggml-org/llama.cpp/commit/5bbe6a9fe9a8796a9389c85accec89dbc4d91e39).
+<div style="text-align: left; margin: 20px 0;">
+    <a href="https://tensorblock.co/waitlist/client" style="display: inline-block; padding: 10px 20px; background-color: #007bff; color: white; text-decoration: none; border-radius: 5px; font-weight: bold;">
+        Run them on the TensorBlock client using your local machine ↗
+    </a>
+</div>
+## Prompt template
+```
+<|im_start|>system
+{system_prompt}<|im_end|>
+<|im_start|>user
+{prompt}<|im_end|>
+<|im_start|>assistant
+```
+## Model file specification
+| Filename | Quant type | File Size | Description |
+| -------- | ---------- | --------- | ----------- |
+| [QwQ-Math-IO-500M-Q2_K.gguf](https://huggingface.co/tensorblock/QwQ-Math-IO-500M-GGUF/blob/main/QwQ-Math-IO-500M-Q2_K.gguf) | Q2_K | 0.339 GB | smallest, significant quality loss - not recommended for most purposes |
+| [QwQ-Math-IO-500M-Q3_K_S.gguf](https://huggingface.co/tensorblock/QwQ-Math-IO-500M-GGUF/blob/main/QwQ-Math-IO-500M-Q3_K_S.gguf) | Q3_K_S | 0.338 GB | very small, high quality loss |
+| [QwQ-Math-IO-500M-Q3_K_M.gguf](https://huggingface.co/tensorblock/QwQ-Math-IO-500M-GGUF/blob/main/QwQ-Math-IO-500M-Q3_K_M.gguf) | Q3_K_M | 0.355 GB | very small, high quality loss |
+| [QwQ-Math-IO-500M-Q3_K_L.gguf](https://huggingface.co/tensorblock/QwQ-Math-IO-500M-GGUF/blob/main/QwQ-Math-IO-500M-Q3_K_L.gguf) | Q3_K_L | 0.369 GB | small, substantial quality loss |
+| [QwQ-Math-IO-500M-Q4_0.gguf](https://huggingface.co/tensorblock/QwQ-Math-IO-500M-GGUF/blob/main/QwQ-Math-IO-500M-Q4_0.gguf) | Q4_0 | 0.352 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [QwQ-Math-IO-500M-Q4_K_S.gguf](https://huggingface.co/tensorblock/QwQ-Math-IO-500M-GGUF/blob/main/QwQ-Math-IO-500M-Q4_K_S.gguf) | Q4_K_S | 0.385 GB | small, greater quality loss |
+| [QwQ-Math-IO-500M-Q4_K_M.gguf](https://huggingface.co/tensorblock/QwQ-Math-IO-500M-GGUF/blob/main/QwQ-Math-IO-500M-Q4_K_M.gguf) | Q4_K_M | 0.398 GB | medium, balanced quality - recommended |
+| [QwQ-Math-IO-500M-Q5_0.gguf](https://huggingface.co/tensorblock/QwQ-Math-IO-500M-GGUF/blob/main/QwQ-Math-IO-500M-Q5_0.gguf) | Q5_0 | 0.397 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [QwQ-Math-IO-500M-Q5_K_S.gguf](https://huggingface.co/tensorblock/QwQ-Math-IO-500M-GGUF/blob/main/QwQ-Math-IO-500M-Q5_K_S.gguf) | Q5_K_S | 0.413 GB | large, low quality loss - recommended |
+| [QwQ-Math-IO-500M-Q5_K_M.gguf](https://huggingface.co/tensorblock/QwQ-Math-IO-500M-GGUF/blob/main/QwQ-Math-IO-500M-Q5_K_M.gguf) | Q5_K_M | 0.420 GB | large, very low quality loss - recommended |
+| [QwQ-Math-IO-500M-Q6_K.gguf](https://huggingface.co/tensorblock/QwQ-Math-IO-500M-GGUF/blob/main/QwQ-Math-IO-500M-Q6_K.gguf) | Q6_K | 0.506 GB | very large, extremely low quality loss |
+| [QwQ-Math-IO-500M-Q8_0.gguf](https://huggingface.co/tensorblock/QwQ-Math-IO-500M-GGUF/blob/main/QwQ-Math-IO-500M-Q8_0.gguf) | Q8_0 | 0.531 GB | very large, extremely low quality loss - not recommended |
+## Downloading instruction
+### Command line
+Firstly, install Huggingface Client
+```shell
+pip install -U "huggingface_hub[cli]"
+```
+Then, downoad the individual model file the a local directory
+```shell
+huggingface-cli download tensorblock/QwQ-Math-IO-500M-GGUF --include "QwQ-Math-IO-500M-Q2_K.gguf" --local-dir MY_LOCAL_DIR
+```
+If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
+```shell
+huggingface-cli download tensorblock/QwQ-Math-IO-500M-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```