Instructions to use gaoqianshen/Qwen-AgentWorld-35B-A3B-Q4_K_M-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use gaoqianshen/Qwen-AgentWorld-35B-A3B-Q4_K_M-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="gaoqianshen/Qwen-AgentWorld-35B-A3B-Q4_K_M-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("gaoqianshen/Qwen-AgentWorld-35B-A3B-Q4_K_M-GGUF", dtype="auto")

llama-cpp-python

How to use gaoqianshen/Qwen-AgentWorld-35B-A3B-Q4_K_M-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="gaoqianshen/Qwen-AgentWorld-35B-A3B-Q4_K_M-GGUF",
	filename="qwen-agentworld-35b-a3b-q4_k_m.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

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

Use Docker

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

LM Studio
Jan

vLLM

How to use gaoqianshen/Qwen-AgentWorld-35B-A3B-Q4_K_M-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "gaoqianshen/Qwen-AgentWorld-35B-A3B-Q4_K_M-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": "gaoqianshen/Qwen-AgentWorld-35B-A3B-Q4_K_M-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

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

SGLang

How to use gaoqianshen/Qwen-AgentWorld-35B-A3B-Q4_K_M-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 "gaoqianshen/Qwen-AgentWorld-35B-A3B-Q4_K_M-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": "gaoqianshen/Qwen-AgentWorld-35B-A3B-Q4_K_M-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 "gaoqianshen/Qwen-AgentWorld-35B-A3B-Q4_K_M-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": "gaoqianshen/Qwen-AgentWorld-35B-A3B-Q4_K_M-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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

Unsloth Studio

How to use gaoqianshen/Qwen-AgentWorld-35B-A3B-Q4_K_M-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 gaoqianshen/Qwen-AgentWorld-35B-A3B-Q4_K_M-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 gaoqianshen/Qwen-AgentWorld-35B-A3B-Q4_K_M-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for gaoqianshen/Qwen-AgentWorld-35B-A3B-Q4_K_M-GGUF to start chatting

How to use gaoqianshen/Qwen-AgentWorld-35B-A3B-Q4_K_M-GGUF with Pi:

Start the llama.cpp server

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

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

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

Run Hermes

hermes

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

Lemonade

How to use gaoqianshen/Qwen-AgentWorld-35B-A3B-Q4_K_M-GGUF with Lemonade:

Pull the model

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

Run and chat with the model

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

List all available models

lemonade list

Does not work with latest llama.cpp

by pcomte - opened 2 days ago

Discussion

pcomte

2 days ago

0.00.260.184 E llama_model_load: error loading model: missing tensor 'blk.40.attn_norm.weight'
0.00.260.310 E llama_model_load_from_file_impl: failed to load model
0.00.260.357 E common_fit_params: encountered an error while trying to fit params to free device memory: failed to load model
0.00.448.882 E llama_model_load: error loading model: missing tensor 'blk.40.attn_norm.weight'
0.00.448.885 E llama_model_load_from_file_impl: failed to load model
0.00.448.886 E common_init_from_params: failed to load model 'qwen-agentworld-35b-a3b-q4_k_m.gguf'
0.00.448.888 E srv    load_model: failed to load model, 'qwen-agentworld-35b-a3b-q4_k_m.gguf'
0.00.448.889 I srv    operator(): operator(): cleaning up before exit...
0.00.449.032 E srv  llama_server: exiting due to model loading error

llama-server --version
version: 9770 (75ad0b23e)
built with AppleClang 21.0.0.21000099 for Darwin arm64

Nobleflame

2 days ago

The gguf was converted incorrectly, gotta wait until somebody posts a real one rather than an autoconvert

freykun

1 day ago

•

edited 1 day ago

Title: llama.cpp crash: missing tensor 'blk.40.attn_norm.weight' (Incorrect GGUF Metadata)

Description:
Hi, thanks for uploading this quant!

I ran into an issue where loading this GGUF in llama.cpp (and standard backends like Ollama/LM Studio) causes a crash on load:

E llama_model_load: error loading model: missing tensor 'blk.40.attn_norm.weight'

The Cause

The quantization script seems to have exported the incorrect metadata for the layer count. The model metadata claims qwen35moe.block_count: 41 and qwen35moe.nextn_predict_layers: 1 (presumably due to the MTP layers). However, the actual tensors for layer 41 (blk.40) and the MTP projection (blk.39.nextn.eh_proj.weight) were not included in the GGUF file. When llama.cpp tries to load them, it hits a missing tensor error.

Temporary Workaround for Users

For anyone else running into this, you can bypass the crash by forcing llama.cpp to ignore the broken metadata and expect the standard 40 blocks with no MTP layers using the --override-kv flag:

llama-server -m qwen-agentworld-35b-a3b-q4_k_m.gguf --override-kv "qwen35moe.block_count=int:40,qwen35moe.nextn_predict_layers=int:0"

To the uploader: A re-quantization with the latest convert_hf_to_gguf.py script that either correctly exports the MTP tensors, or correctly strips them out and sets the metadata to 40 blocks, should permanently fix this for all users.

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