Instructions to use Hal0ai/hal0-brain-sft-fpx4-agent with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Hal0ai/hal0-brain-sft-fpx4-agent with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Hal0ai/hal0-brain-sft-fpx4-agent",
	filename="model.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/hal0-brain-sft-fpx4-agent 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/hal0-brain-sft-fpx4-agent
# Run inference directly in the terminal:
llama cli -hf Hal0ai/hal0-brain-sft-fpx4-agent

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Hal0ai/hal0-brain-sft-fpx4-agent
# Run inference directly in the terminal:
llama cli -hf Hal0ai/hal0-brain-sft-fpx4-agent

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/hal0-brain-sft-fpx4-agent
# Run inference directly in the terminal:
./llama-cli -hf Hal0ai/hal0-brain-sft-fpx4-agent

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/hal0-brain-sft-fpx4-agent
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Hal0ai/hal0-brain-sft-fpx4-agent

Use Docker

docker model run hf.co/Hal0ai/hal0-brain-sft-fpx4-agent

LM Studio
Jan

vLLM

How to use Hal0ai/hal0-brain-sft-fpx4-agent with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Hal0ai/hal0-brain-sft-fpx4-agent"
# 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/hal0-brain-sft-fpx4-agent",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Hal0ai/hal0-brain-sft-fpx4-agent

Ollama
How to use Hal0ai/hal0-brain-sft-fpx4-agent with Ollama:
```
ollama run hf.co/Hal0ai/hal0-brain-sft-fpx4-agent
```

Unsloth Studio

How to use Hal0ai/hal0-brain-sft-fpx4-agent 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/hal0-brain-sft-fpx4-agent 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/hal0-brain-sft-fpx4-agent to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Hal0ai/hal0-brain-sft-fpx4-agent to start chatting

How to use Hal0ai/hal0-brain-sft-fpx4-agent with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Hal0ai/hal0-brain-sft-fpx4-agent

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/hal0-brain-sft-fpx4-agent"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Hal0ai/hal0-brain-sft-fpx4-agent 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/hal0-brain-sft-fpx4-agent

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/hal0-brain-sft-fpx4-agent

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use Hal0ai/hal0-brain-sft-fpx4-agent with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Hal0ai/hal0-brain-sft-fpx4-agent

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/hal0-brain-sft-fpx4-agent" \
  --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/hal0-brain-sft-fpx4-agent with Docker Model Runner:
```
docker model run hf.co/Hal0ai/hal0-brain-sft-fpx4-agent
```

Lemonade

How to use Hal0ai/hal0-brain-sft-fpx4-agent with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Hal0ai/hal0-brain-sft-fpx4-agent

Run and chat with the model

lemonade run user.hal0-brain-sft-fpx4-agent-{{QUANT_TAG}}

List all available models

lemonade list

hal0-brain-sft-fpx4-agent (GGUF ROCmFP4)

ROCmFP4-quantized GGUF of Hal0ai/hal0-brain-sft for the hal0 agent slot on AMD Strix Halo / RDNA accelerators.

The quant type is Q4_0_ROCMFP4_STRIX_LEAN (the charlie12345/rocmfp4-llama fork's variant of llama.cpp's quantize). Standard gguf-py reports the tensor type as 101 (undefined in the stock enum) — this file requires the ROCm FP4 fork of llama-server, not upstream.

How hal0 uses this file

The hal0 agent slot is the default LLM anchor (ADR-0023). On AMD ROCm boxes (Strix Halo, RDNA3+), the recommended assign is this GGUF, loaded into a hal0-slot@agent.service container using the hal0-rocmfpx runtime image:

hal0 model pull Hal0ai/hal0-brain-sft-fpx4-agent-GGUF
hal0 model assign hal0-brain-sft-fpx4-agent --slot agent
hal0 slot load agent

The container's hal0-rocmfpx image (ghcr.io/hal0ai/hal0-rocmfpx) bundles a llama-server built with the ROCmFP4 patch and /dev/kfd + /dev/dri passed through, so the slot picks up FP4 matmul automatically. Suggested flags (from the r105 brain-agent-fpx slot profile):

--jinja -fa on -ngl 99 -dev ROCm0 -b 512 -ub 512 \
--threads 16 --threads-batch 32 --no-mmap --metrics --no-webui

Required runtime

This file uses the AMD ROCm FP4 tensor type (raw_dtype=101) which is not recognized by upstream llama.cpp. You need one of:

charlie12345/rocmfp4-llama — checkout mtp-rocmfp4-strix and build:

git clone https://github.com/charlie12345/rocmfp4-llama.git
cd rocmfp4-llama && git checkout mtp-rocmfp4-strix
env JOBS=16 scripts/build-strix-rocmfp4-mtp.sh

A downstream llama.cpp / llama-server that has merged the ROCm FP4 patch.
hal0's hal0-quant-fc toolbox image, which bundles a compatible binary.
The ghcr.io/hal0ai/hal0-rocmfpx hal0-slot image (recommended for the hal0 stack).

Usage — hal0-slot (the official wiring, ROCm container)

# 1. Pull the GGUF into hal0's model store
hal0 model pull Hal0ai/hal0-brain-sft-fpx4-agent-GGUF

# 2. Assign to the agent slot
hal0 model assign hal0-brain-sft-fpx4-agent --slot agent

# 3. Load — container runtime image is selected from slot config
#    (hal0.toml [slots.agent] profile="chat" device="gpu-vulkan" → hal0-rocmfpx image on ROCm boxes)
hal0 slot load agent

# 4. Verify
curl http://127.0.0.1:8081/v1/models

Usage — direct llama-cli (from the ROCmFP4 fork build)

./build-strix-rocmfp4-mtp/bin/llama-cli -m model.gguf \
    -p "What does the hal0 'agent' slot default to?" -n 256 --jinja

Usage — direct llama-server (production ROCm)

./build-strix-rocmfp4-mtp/bin/llama-server \
    -m model.gguf \
    --jinja -fa on -ngl 99 -dev ROCm0 \
    -b 512 -ub 512 --threads 16 --threads-batch 32 \
    --no-mmap --metrics --no-webui \
    --port 8081

Tradeoffs vs. base

	F16 GGUF	ROCmFP4 (this)	F16 safetensors
Size	2.0 GB	608 MB	2.1 GB
Quality	reference	~minor loss (4-bit)	reference
Hardware	any	AMD ROCm (Strix / RDNA)	any
Loader	upstream llama.cpp	ROCm FP4 fork or `hal0-rocmfpx` image	transformers

Model details


Base model	`Hal0ai/hal0-brain-sft` (BF16 safetensors)
Relation	quantized
Architecture	LlamaForCausalLM, 1.5B params
Quant type	`Q4_0_ROCMFP4_STRIX_LEAN` (AMD ROCm FP4 fork)
SHA-256	`2579246ef97d547ff91c2d5a679ea1792ebdb11836e4379380219c1ee7983b04`
File size	608 MB
License	Apache-2.0

Hal0ai/hal0-brain-sft — BF16 safetensors (base)
Hal0ai/hal0-brain-sft-GGUF — F16 GGUF (upstream llama.cpp)
Hal0ai/hal0-brain-sft-fpx8-agent — Q8_0 GGUF (agent slot, CPU/VRAM-tight)
Collection: hal0-brain

License

Apache-2.0.

Provenance

Repo: Hal0ai/hal0-brain-sft-fpx4-agent
Org: Hal0ai
Project: https://github.com/Hal0ai/hal0
Build: charlie12345/rocmfp4-llama @ mtp-rocmfp4-strix

Downloads last month: 22

GGUF

Model size

1B params

Architecture

llama

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Model tree for Hal0ai/hal0-brain-sft-fpx4-agent

Base model

Hal0ai/hal0-brain-sft

Quantized

(4)

this model

Hal0ai
/

hal0-brain-sft-fpx4-agent

hal0-brain-sft-fpx4-agent (GGUF ROCmFP4)

How hal0 uses this file

Required runtime

Usage — hal0-slot (the official wiring, ROCm container)

Usage — direct llama-cli (from the ROCmFP4 fork build)

Usage — direct llama-server (production ROCm)

Tradeoffs vs. base

Model details

Related

License

Provenance

Model tree for Hal0ai/hal0-brain-sft-fpx4-agent