Instructions to use ivgranite/Qwen-AgentWorld-35B-A3B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use ivgranite/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 ivgranite/Qwen-AgentWorld-35B-A3B-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf ivgranite/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 ivgranite/Qwen-AgentWorld-35B-A3B-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf ivgranite/Qwen-AgentWorld-35B-A3B-GGUF:Q4_K_M
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf ivgranite/Qwen-AgentWorld-35B-A3B-GGUF:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama cli -hf ivgranite/Qwen-AgentWorld-35B-A3B-GGUF:Q4_K_M
Use Docker
docker model run hf.co/ivgranite/Qwen-AgentWorld-35B-A3B-GGUF:Q4_K_M
- Llama new
- LM Studio
- Jan
- vLLM
How to use ivgranite/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 "ivgranite/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": "ivgranite/Qwen-AgentWorld-35B-A3B-GGUF", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/ivgranite/Qwen-AgentWorld-35B-A3B-GGUF:Q4_K_M
- Ollama
How to use ivgranite/Qwen-AgentWorld-35B-A3B-GGUF with Ollama:
ollama run hf.co/ivgranite/Qwen-AgentWorld-35B-A3B-GGUF:Q4_K_M
- Unsloth Desktop
- Pi
How to use ivgranite/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 ivgranite/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:9931/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "ivgranite/Qwen-AgentWorld-35B-A3B-GGUF:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use ivgranite/Qwen-AgentWorld-35B-A3B-GGUF with Docker Model Runner:
docker model run hf.co/ivgranite/Qwen-AgentWorld-35B-A3B-GGUF:Q4_K_M
- Lemonade
How to use ivgranite/Qwen-AgentWorld-35B-A3B-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull ivgranite/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 ivgranite/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 ivgranite/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://127.0.0.1:9931/v1 hermes config set model.default ivgranite/Qwen-AgentWorld-35B-A3B-GGUF:Q4_K_M
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use ivgranite/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 ivgranite/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://127.0.0.1:9931/v1 \ --custom-model-id "ivgranite/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"
Qwen-AgentWorld-35B-A3B GGUF
GGUF quantization of Qwen/Qwen-AgentWorld-35B-A3B, a native language world model trained for agentic environment simulation across seven domains (Terminal, MCP, Search, SWE, Web, Android, OS).
Why this conversion exists
Most community GGUF conversions of this model have a critical bug: they set block_count=41 (inheriting mtp_num_hidden_layers: 1 from the Qwen3.5 config template), but the original safetensors contain zero MTP/nextn tensors. This causes llama.cpp to fail with:
error loading model: missing tensor 'blk.40.attn_norm.weight'
This conversion was done from the original safetensors using llama.cpp's convert_hf_to_gguf.py with --no-mtp, which correctly sets block_count=40 and skips the non-existent MTP layer.
For additional quants (Q2_K, Q6_K, Q8_0, BF16, imatrix), groxaxo's conversion is also correct and worth checking out.
Conversion details
Toolchain: llama.cpp release b9484 (commit 63e66fdd2)
# Download original model
hf download Qwen/Qwen-AgentWorld-35B-A3B --local-dir ./source
# Convert to BF16 GGUF (no MTP โ model doesn't include MTP weights)
python convert_hf_to_gguf.py ./source \
--outfile agentworld-bf16.gguf \
--outtype bf16 \
--no-mtp
# Quantize
llama-quantize agentworld-bf16.gguf Qwen-AgentWorld-35B-A3B-Q4_K_M.gguf Q4_K_M
Verified: 733 tensors, block_count=40, no nextn_predict metadata.
Available quants
| Filename | Quant type | File Size | Description |
|---|---|---|---|
| Qwen-AgentWorld-35B-A3B-Q4_K_M.gguf | Q4_K_M | 19.7GB | Good quality, default for most use cases, recommended. |
Model info
- Architecture: Qwen3.5 MoE (Gated DeltaNet + Gated Attention hybrid)
- Parameters: 35B total / 3B active
- Layers: 40 (10 ร [3 linear attention + 1 full attention])
- Experts: 256 (8 routed + 1 shared)
- Context: 262,144 tokens
- Thinking mode: Enabled by default (
<think>...</think>)
Usage
# llama.cpp
llama-server \
-m Qwen-AgentWorld-35B-A3B-Q4_K_M.gguf \
--reasoning on --reasoning-budget 32768 \
-c 131072 -ngl 999 -fa on \
--cache-type-k q4_0 --cache-type-v q4_0 \
--jinja
# Recommended sampling
temperature: 0.6, top_p: 0.95, top_k: 20
Prompt format
<|im_start|>system
{world_model_system_prompt}<|im_end|>
<|im_start|>user
{agent_action}<|im_end|>
<|im_start|>assistant
<think>
Domain-specific system prompts for all 7 domains (Terminal, MCP, Search, SWE, Web, Android, OS) are available in the official GitHub repository.
Evaluation
Run AgentWorldBench (2,170 samples, 7 domains) with the official eval framework:
git clone https://github.com/QwenLM/Qwen-AgentWorld.git
hf download Qwen/AgentWorldBench --repo-type dataset --local-dir ./AgentWorldBench
cd Qwen-AgentWorld/eval
python eval.py infer \
--data-dir ../AgentWorldBench \
--model-base-url http://localhost:8080/v1 \
--model-name Qwen-AgentWorld-35B-A3B \
--output-dir ./results
Original model
See Qwen/Qwen-AgentWorld-35B-A3B, the blog post, and the technical report (arXiv:2606.24597) for full details.
- Downloads last month
- 50
4-bit
Model tree for ivgranite/Qwen-AgentWorld-35B-A3B-GGUF
Base model
Qwen/Qwen3.5-35B-A3B-Base