Instructions to use DhruvalLabs/Qwen-AgentWorld-35B-A3B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DhruvalLabs/Qwen-AgentWorld-35B-A3B-GGUF with Transformers:

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

pipe = pipeline("image-text-to-text", model="DhruvalLabs/Qwen-AgentWorld-35B-A3B-GGUF")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("DhruvalLabs/Qwen-AgentWorld-35B-A3B-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use DhruvalLabs/Qwen-AgentWorld-35B-A3B-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 DhruvalLabs/Qwen-AgentWorld-35B-A3B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf DhruvalLabs/Qwen-AgentWorld-35B-A3B-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 DhruvalLabs/Qwen-AgentWorld-35B-A3B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf DhruvalLabs/Qwen-AgentWorld-35B-A3B-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 DhruvalLabs/Qwen-AgentWorld-35B-A3B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf DhruvalLabs/Qwen-AgentWorld-35B-A3B-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 DhruvalLabs/Qwen-AgentWorld-35B-A3B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf DhruvalLabs/Qwen-AgentWorld-35B-A3B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/DhruvalLabs/Qwen-AgentWorld-35B-A3B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use DhruvalLabs/Qwen-AgentWorld-35B-A3B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DhruvalLabs/Qwen-AgentWorld-35B-A3B-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": "DhruvalLabs/Qwen-AgentWorld-35B-A3B-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/DhruvalLabs/Qwen-AgentWorld-35B-A3B-GGUF:Q4_K_M

SGLang

How to use DhruvalLabs/Qwen-AgentWorld-35B-A3B-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 "DhruvalLabs/Qwen-AgentWorld-35B-A3B-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": "DhruvalLabs/Qwen-AgentWorld-35B-A3B-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 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 "DhruvalLabs/Qwen-AgentWorld-35B-A3B-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": "DhruvalLabs/Qwen-AgentWorld-35B-A3B-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"
						}
					}
				]
			}
		]
	}'

Ollama
How to use DhruvalLabs/Qwen-AgentWorld-35B-A3B-GGUF with Ollama:
```
ollama run hf.co/DhruvalLabs/Qwen-AgentWorld-35B-A3B-GGUF:Q4_K_M
```
Unsloth Desktop

How to use DhruvalLabs/Qwen-AgentWorld-35B-A3B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf DhruvalLabs/Qwen-AgentWorld-35B-A3B-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "DhruvalLabs/Qwen-AgentWorld-35B-A3B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use DhruvalLabs/Qwen-AgentWorld-35B-A3B-GGUF with Docker Model Runner:
```
docker model run hf.co/DhruvalLabs/Qwen-AgentWorld-35B-A3B-GGUF:Q4_K_M
```

Lemonade

How to use DhruvalLabs/Qwen-AgentWorld-35B-A3B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull DhruvalLabs/Qwen-AgentWorld-35B-A3B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen-AgentWorld-35B-A3B-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use DhruvalLabs/Qwen-AgentWorld-35B-A3B-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 DhruvalLabs/Qwen-AgentWorld-35B-A3B-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 DhruvalLabs/Qwen-AgentWorld-35B-A3B-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use DhruvalLabs/Qwen-AgentWorld-35B-A3B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf DhruvalLabs/Qwen-AgentWorld-35B-A3B-GGUF:Q4_K_M

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 "DhruvalLabs/Qwen-AgentWorld-35B-A3B-GGUF:Q4_K_M" \
  --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"

error loading Q8_0 weights

by khimaros - opened Jun 24

Discussion

khimaros

Jun 24

0.01.783.915 E llama_model_load: error loading model: missing tensor 'blk.40.attn_norm.weight'
0.01.783.944 E llama_model_load_from_file_impl: failed to load model

DhruvalLabs

Owner Jun 24

•

edited Jun 24

Hi! Thank you so much for reporting this and bringing it to my attention. You were completely right to flag this, and I did a deep dive into the architecture to find out why it was crashing.

👍✅✅✅You can redownload and run, it will run smoothly without any error.

What happened:
The issue actually isn't a bad upload or corrupted weights, but rather a bug in the mainline llama.cpp conversion script regarding Qwen's new MTP (Multi-Token Prediction) layers.

During the original GGUF conversion, the script read the Hugging Face config, saw the MTP head, and wrote block_count = 41 into the GGUF metadata header. However, it did not actually pack those extra MTP weights into the file. The tensor data stops perfectly at layer 39. When your local runner (Ollama/LM Studio/llama.cpp) booted the model, the header told it to look for a 40th layer that didn't physically exist, causing the fatal missing tensor 'blk.40.attn_norm.weight' crash.

The Fix:
The actual model weights are 100% healthy. To resolve this without losing data, I ran a surgical binary patch directly on the GGUF metadata headers of the files to correct qwen35moe.block_count to 40 and nextn_predict_layers to 0.

I have tested the patched files on my end, and the inference engine now correctly bypasses the phantom layer, builds the graph, and generates text flawlessly.

Next Steps:
I have patched all the .gguf files and pushed them back to this repository. Please delete your broken local copy, download the newly updated file, and it will load perfectly for you!

Thanks again for helping track this down!

DhruvalLabs

Owner Jun 24

wait few minutes, New fixed models will be uploaded within 1 hour.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment