Instructions to use Hal0ai/Qwen-AgentWorld-Hal0-35B-A3B-ROCmFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Hal0ai/Qwen-AgentWorld-Hal0-35B-A3B-ROCmFP4 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Hal0ai/Qwen-AgentWorld-Hal0-35B-A3B-ROCmFP4",
	filename="Qwen-AgentWorld-35B-A3B-ROCmFP4-STRIX_LEAN.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 Hal0ai/Qwen-AgentWorld-Hal0-35B-A3B-ROCmFP4 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 Hal0ai/Qwen-AgentWorld-Hal0-35B-A3B-ROCmFP4
# Run inference directly in the terminal:
llama cli -hf Hal0ai/Qwen-AgentWorld-Hal0-35B-A3B-ROCmFP4

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Hal0ai/Qwen-AgentWorld-Hal0-35B-A3B-ROCmFP4
# Run inference directly in the terminal:
llama cli -hf Hal0ai/Qwen-AgentWorld-Hal0-35B-A3B-ROCmFP4

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 Hal0ai/Qwen-AgentWorld-Hal0-35B-A3B-ROCmFP4
# Run inference directly in the terminal:
./llama-cli -hf Hal0ai/Qwen-AgentWorld-Hal0-35B-A3B-ROCmFP4

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 Hal0ai/Qwen-AgentWorld-Hal0-35B-A3B-ROCmFP4
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Hal0ai/Qwen-AgentWorld-Hal0-35B-A3B-ROCmFP4

Use Docker

docker model run hf.co/Hal0ai/Qwen-AgentWorld-Hal0-35B-A3B-ROCmFP4

LM Studio
Jan

vLLM

How to use Hal0ai/Qwen-AgentWorld-Hal0-35B-A3B-ROCmFP4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Hal0ai/Qwen-AgentWorld-Hal0-35B-A3B-ROCmFP4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Hal0ai/Qwen-AgentWorld-Hal0-35B-A3B-ROCmFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Hal0ai/Qwen-AgentWorld-Hal0-35B-A3B-ROCmFP4

Ollama
How to use Hal0ai/Qwen-AgentWorld-Hal0-35B-A3B-ROCmFP4 with Ollama:
```
ollama run hf.co/Hal0ai/Qwen-AgentWorld-Hal0-35B-A3B-ROCmFP4
```

Unsloth Studio

How to use Hal0ai/Qwen-AgentWorld-Hal0-35B-A3B-ROCmFP4 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 Hal0ai/Qwen-AgentWorld-Hal0-35B-A3B-ROCmFP4 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 Hal0ai/Qwen-AgentWorld-Hal0-35B-A3B-ROCmFP4 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Hal0ai/Qwen-AgentWorld-Hal0-35B-A3B-ROCmFP4 to start chatting

How to use Hal0ai/Qwen-AgentWorld-Hal0-35B-A3B-ROCmFP4 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Hal0ai/Qwen-AgentWorld-Hal0-35B-A3B-ROCmFP4

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": "Hal0ai/Qwen-AgentWorld-Hal0-35B-A3B-ROCmFP4"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Hal0ai/Qwen-AgentWorld-Hal0-35B-A3B-ROCmFP4 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Hal0ai/Qwen-AgentWorld-Hal0-35B-A3B-ROCmFP4

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 Hal0ai/Qwen-AgentWorld-Hal0-35B-A3B-ROCmFP4

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use Hal0ai/Qwen-AgentWorld-Hal0-35B-A3B-ROCmFP4 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Hal0ai/Qwen-AgentWorld-Hal0-35B-A3B-ROCmFP4

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 "Hal0ai/Qwen-AgentWorld-Hal0-35B-A3B-ROCmFP4" \
  --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 Hal0ai/Qwen-AgentWorld-Hal0-35B-A3B-ROCmFP4 with Docker Model Runner:
```
docker model run hf.co/Hal0ai/Qwen-AgentWorld-Hal0-35B-A3B-ROCmFP4
```

Lemonade

How to use Hal0ai/Qwen-AgentWorld-Hal0-35B-A3B-ROCmFP4 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Hal0ai/Qwen-AgentWorld-Hal0-35B-A3B-ROCmFP4

Run and chat with the model

lemonade run user.Qwen-AgentWorld-Hal0-35B-A3B-ROCmFP4-{{QUANT_TAG}}

List all available models

lemonade list

Qwen-AgentWorld-Hal0-35B-A3B-ROCmFP4 / README.md

thinmint

Add model card

d913a1d verified 14 days ago

preview code

Raw

History Blame Contribute Delete

1.92 kB

metadata

base_model: Qwen/Qwen-AgentWorld-35B-A3B
base_model_relation: quantized
license: apache-2.0
library_name: gguf
pipeline_tag: text-generation
quantized_by: Hal0ai
tags:
  - gguf
  - rocmfp4
  - qwen35moe
  - moe
  - world-model
  - strix-halo
  - amd

Qwen-AgentWorld-Hal0-35B-A3B-ROCmFP4

A ROCmFP4 (Q4_0_ROCMFP4_STRIX_LEAN, ~4.29 bpw) GGUF quant of Qwen/Qwen-AgentWorld-35B-A3B — a 35B-A3B Mixture-of-Experts (qwen35moe) world-model, 262K context.

Built for AMD Strix Halo (gfx1151) unified-memory inference on the hal0 agent platform.

⚠️ Requires the ROCmFP4 llama.cpp fork — not upstream

ROCmFP4 is an experimental, fork-specific quantization format (UE4M3-scale FP4). It is not loadable by stock llama.cpp or standard GGUF tooling — those will fail with 101 is not a valid GGMLQuantizationType.

Run it with either:

the hal0 Strix Halo toolbox image ghcr.io/hal0ai/amd-strix-halo-toolboxes:rocm-7.2.4-rocmfp4-server, or
a build of the rocmfp4-llama fork (branch mtp-rocmfp4-strix), targeting gfx1151.

Details


Architecture	`qwen35moe` (35B total / ~3B active, MoE)
Quant	`Q4_0_ROCMFP4_STRIX_LEAN` (~4.38 bpw target; 4.29 bpw measured)
Recipe	ROCmFP4 experts/FFN + Strix K/V + Q5_K token embeddings
File size	~17.3 GiB (from 66 GiB BF16)
MTP	No (plain quant, no speculative-decode draft head)
Context	262144
Base	Qwen/Qwen-AgentWorld-35B-A3B (Apache-2.0)

Provenance

Quantized from the BF16 GGUF in unsloth/Qwen-AgentWorld-35B-A3B-GGUF, using that repo's importance matrix (imatrix_unsloth.gguf), via the hal0 ROCmFP4 quantize pipeline (llama-quantize --imatrix ... Q4_0_ROCMFP4_STRIX_LEAN).