Instructions to use jukofyork/Qwen3-0.6B-YaRN-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jukofyork/Qwen3-0.6B-YaRN-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="jukofyork/Qwen3-0.6B-YaRN-GGUF",
	filename="Qwen3-0.6B-128k-Q4_0.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use jukofyork/Qwen3-0.6B-YaRN-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 jukofyork/Qwen3-0.6B-YaRN-GGUF:Q4_0
# Run inference directly in the terminal:
llama cli -hf jukofyork/Qwen3-0.6B-YaRN-GGUF:Q4_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf jukofyork/Qwen3-0.6B-YaRN-GGUF:Q4_0
# Run inference directly in the terminal:
llama cli -hf jukofyork/Qwen3-0.6B-YaRN-GGUF:Q4_0

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 jukofyork/Qwen3-0.6B-YaRN-GGUF:Q4_0
# Run inference directly in the terminal:
./llama-cli -hf jukofyork/Qwen3-0.6B-YaRN-GGUF:Q4_0

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 jukofyork/Qwen3-0.6B-YaRN-GGUF:Q4_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf jukofyork/Qwen3-0.6B-YaRN-GGUF:Q4_0

Use Docker

docker model run hf.co/jukofyork/Qwen3-0.6B-YaRN-GGUF:Q4_0

LM Studio
Jan
Ollama
How to use jukofyork/Qwen3-0.6B-YaRN-GGUF with Ollama:
```
ollama run hf.co/jukofyork/Qwen3-0.6B-YaRN-GGUF:Q4_0
```

Unsloth Studio

How to use jukofyork/Qwen3-0.6B-YaRN-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 jukofyork/Qwen3-0.6B-YaRN-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 jukofyork/Qwen3-0.6B-YaRN-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for jukofyork/Qwen3-0.6B-YaRN-GGUF to start chatting

How to use jukofyork/Qwen3-0.6B-YaRN-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf jukofyork/Qwen3-0.6B-YaRN-GGUF:Q4_0

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": "jukofyork/Qwen3-0.6B-YaRN-GGUF:Q4_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use jukofyork/Qwen3-0.6B-YaRN-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 jukofyork/Qwen3-0.6B-YaRN-GGUF:Q4_0

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 jukofyork/Qwen3-0.6B-YaRN-GGUF:Q4_0

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use jukofyork/Qwen3-0.6B-YaRN-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf jukofyork/Qwen3-0.6B-YaRN-GGUF:Q4_0

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 "jukofyork/Qwen3-0.6B-YaRN-GGUF:Q4_0" \
  --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"

Docker Model Runner
How to use jukofyork/Qwen3-0.6B-YaRN-GGUF with Docker Model Runner:
```
docker model run hf.co/jukofyork/Qwen3-0.6B-YaRN-GGUF:Q4_0
```

Lemonade

How to use jukofyork/Qwen3-0.6B-YaRN-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull jukofyork/Qwen3-0.6B-YaRN-GGUF:Q4_0

Run and chat with the model

lemonade run user.Qwen3-0.6B-YaRN-GGUF-Q4_0

List all available models

lemonade list

These are YaRN extended versions of Qwen3-0.6B for use with:

The new Qwen3-235B-A22B-Instruct-2507, Qwen3-235B-A22B-Thinking-2507 and Qwen3-Coder-480B-A35B-Instruct models that support up to 256k context length.
(Potentially) any model via Universal Assisted Generation added to llama.cpp in #12635.

I've included the Q4_0 quants for 4 different context lengths:

NOTE: Because llama.cpp uses "static-YaRN" the scaling factor remains constant regardless of input length:

Only use the YaRN-extended versions when processing long contexts is required.
Use the smallest YaRN-extension possible.

How these were created

To extend the context to 64k:

Edit the config.json file:

  "max_position_embeddings": 65536,
  ...
  "rope_scaling": {
    "factor": 2.0,
    "original_max_position_embeddings": 32768,
    "type": "yarn"
  },

Convert and quantize:

./llama.cpp/convert_hf_to_gguf.py --outtype auto --outfile  Qwen3-0.6B-64k-BF16.gguf Qwen3-0.6B
./llama.cpp/build/bin/llama-quantize Qwen3-0.6B-64k-BF16.gguf Qwen3-0.6B-64k-Q4_0.gguf Q4_0 44

To extend the context to 128k:

Edit the config.json file:

  "max_position_embeddings": 131072,
  ...
  "rope_scaling": {
    "factor": 4.0,
    "original_max_position_embeddings": 32768,
    "type": "yarn"
  },

Convert and quantize:

./llama.cpp/convert_hf_to_gguf.py --outtype auto --outfile  Qwen3-0.6B-128k-BF16.gguf Qwen3-0.6B
./llama.cpp/build/bin/llama-quantize Qwen3-0.6B-128k-BF16.gguf Qwen3-0.6B-128k-Q4_0.gguf Q4_0 44

To extend the context to 256k:

Edit the config.json file:

  "max_position_embeddings": 262144,
  ...
  "rope_scaling": {
    "factor": 8.0,
    "original_max_position_embeddings": 32768,
    "type": "yarn"
  },

Convert and quantize:

./llama.cpp/convert_hf_to_gguf.py --outtype auto --outfile  Qwen3-0.6B-256k-BF16.gguf Qwen3-0.6B
./llama.cpp/build/bin/llama-quantize Qwen3-0.6B-256k-BF16.gguf Qwen3-0.6B-256k-Q4_0.gguf Q4_0 44

How to patch the GGUF files for other context lengths

First work out the new scale factor, eg: for 1M context (2^20 = 1048576) we need 1048576/32768 = 32.0.
Copy one of the existing YaRN-extended GGUF files (ie: NOT Qwen3-0.6B-32k-Q4_0.gguf!) and patch it using gguf_set_metadata.py:

./llama.cpp/gguf-py/gguf/scripts/gguf_set_metadata.py Qwen3-0.6B-1M-Q4_0.gguf qwen3.context_length 1048576
./llama.cpp/gguf-py/gguf/scripts/gguf_set_metadata.py Qwen3-0.6B-1M-Q4_0.gguf qwen3.rope.scaling.factor 32.0

Check the patch has worked using gguf_dump.py:

./llama.cpp/gguf-py/gguf/scripts/gguf_dump.py --no-tensors  Qwen3-0.6B-1M-Q4_0.gguf

INFO:gguf-dump:* Loading: Qwen3-0.6B-1M-Q4_0.gguf
* File is LITTLE endian, script is running on a LITTLE endian host.
* Dumping 40 key/value pair(s)
      1: UINT32     |        1 | GGUF.version = 3
      2: UINT64     |        1 | GGUF.tensor_count = 311
      3: UINT64     |        1 | GGUF.kv_count = 37
      4: STRING     |        1 | general.architecture = 'qwen3'
      5: STRING     |        1 | general.type = 'model'
      6: STRING     |        1 | general.name = 'Qwen3 0.6B'
      7: STRING     |        1 | general.basename = 'Qwen3'
      8: STRING     |        1 | general.size_label = '0.6B'
      9: STRING     |        1 | general.license = 'apache-2.0'
     10: STRING     |        1 | general.license.link = 'https://huggingface.co/Qwen/Qwen3-0.6B/blob/main/LICENSE'
     11: UINT32     |        1 | general.base_model.count = 1
     12: STRING     |        1 | general.base_model.0.name = 'Qwen3 0.6B Base'
     13: STRING     |        1 | general.base_model.0.organization = 'Qwen'
     14: STRING     |        1 | general.base_model.0.repo_url = 'https://huggingface.co/Qwen/Qwen3-0.6B-Base'
     15: [STRING]   |        1 | general.tags = ['text-generation']
     16: UINT32     |        1 | qwen3.block_count = 28
     17: UINT32     |        1 | qwen3.context_length = 1048576
     18: UINT32     |        1 | qwen3.embedding_length = 1024
     19: UINT32     |        1 | qwen3.feed_forward_length = 3072
     20: UINT32     |        1 | qwen3.attention.head_count = 16
     21: UINT32     |        1 | qwen3.attention.head_count_kv = 8
     22: FLOAT32    |        1 | qwen3.rope.freq_base = 1000000.0
     23: FLOAT32    |        1 | qwen3.attention.layer_norm_rms_epsilon = 9.999999974752427e-07
     24: UINT32     |        1 | qwen3.attention.key_length = 128
     25: UINT32     |        1 | qwen3.attention.value_length = 128
     26: STRING     |        1 | qwen3.rope.scaling.type = 'yarn'
     27: FLOAT32    |        1 | qwen3.rope.scaling.factor = 32.0
     28: UINT32     |        1 | qwen3.rope.scaling.original_context_length = 32768
     29: STRING     |        1 | tokenizer.ggml.model = 'gpt2'
     30: STRING     |        1 | tokenizer.ggml.pre = 'qwen2'
     31: [STRING]   |   151936 | tokenizer.ggml.tokens = ['!', '"', '#', '$', '%', '&', ...]
     32: [INT32]    |   151936 | tokenizer.ggml.token_type = [1, 1, 1, 1, 1, 1, ...]
     33: [STRING]   |   151387 | tokenizer.ggml.merges = ['Ġ Ġ', 'ĠĠ ĠĠ', 'i n', 'Ġ t', 'ĠĠĠĠ ĠĠĠĠ', 'e r', ...]
     34: UINT32     |        1 | tokenizer.ggml.eos_token_id = 151645
     35: UINT32     |        1 | tokenizer.ggml.padding_token_id = 151643
     36: UINT32     |        1 | tokenizer.ggml.bos_token_id = 151643
     37: BOOL       |        1 | tokenizer.ggml.add_bos_token = False
     38: STRING     |        1 | tokenizer.chat_template = "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%-..."
     39: UINT32     |        1 | general.quantization_version = 2
     40: UINT32     |        1 | general.file_type = 2