Instructions to use Hal0ai/FastContext-Hal0-4B-ROCmFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Hal0ai/FastContext-Hal0-4B-ROCmFP4 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Hal0ai/FastContext-Hal0-4B-ROCmFP4",
	filename="FastContext-4B-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/FastContext-Hal0-4B-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/FastContext-Hal0-4B-ROCmFP4
# Run inference directly in the terminal:
llama cli -hf Hal0ai/FastContext-Hal0-4B-ROCmFP4

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Hal0ai/FastContext-Hal0-4B-ROCmFP4
# Run inference directly in the terminal:
llama cli -hf Hal0ai/FastContext-Hal0-4B-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/FastContext-Hal0-4B-ROCmFP4
# Run inference directly in the terminal:
./llama-cli -hf Hal0ai/FastContext-Hal0-4B-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/FastContext-Hal0-4B-ROCmFP4
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Hal0ai/FastContext-Hal0-4B-ROCmFP4

Use Docker

docker model run hf.co/Hal0ai/FastContext-Hal0-4B-ROCmFP4

LM Studio
Jan

vLLM

How to use Hal0ai/FastContext-Hal0-4B-ROCmFP4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Hal0ai/FastContext-Hal0-4B-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/FastContext-Hal0-4B-ROCmFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Hal0ai/FastContext-Hal0-4B-ROCmFP4

Ollama
How to use Hal0ai/FastContext-Hal0-4B-ROCmFP4 with Ollama:
```
ollama run hf.co/Hal0ai/FastContext-Hal0-4B-ROCmFP4
```

Unsloth Studio

How to use Hal0ai/FastContext-Hal0-4B-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/FastContext-Hal0-4B-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/FastContext-Hal0-4B-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/FastContext-Hal0-4B-ROCmFP4 to start chatting

How to use Hal0ai/FastContext-Hal0-4B-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/FastContext-Hal0-4B-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/FastContext-Hal0-4B-ROCmFP4"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Hal0ai/FastContext-Hal0-4B-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/FastContext-Hal0-4B-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/FastContext-Hal0-4B-ROCmFP4

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use Hal0ai/FastContext-Hal0-4B-ROCmFP4 with Docker Model Runner:
```
docker model run hf.co/Hal0ai/FastContext-Hal0-4B-ROCmFP4
```

Lemonade

How to use Hal0ai/FastContext-Hal0-4B-ROCmFP4 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Hal0ai/FastContext-Hal0-4B-ROCmFP4

Run and chat with the model

lemonade run user.FastContext-Hal0-4B-ROCmFP4-{{QUANT_TAG}}

List all available models

lemonade list

FastContext-Hal0-4B — ROCmFP4 (STRIX_LEAN)

A 4-bit ROCmFP4 quantization of microsoft/FastContext-1.0-4B-SFT, a lightweight repository-exploration subagent (Qwen3-4B backbone) for LLM coding agents.

Quantized and validated on AMD Strix Halo (Ryzen AI MAX+ 395 / Radeon 8060S, gfx1151) using hal0ai/amd-strix-halo-toolboxes 🛠️.

⚠️ Read this first — special runtime required

This file uses the experimental Q4_0_ROCMFP4 GGUF tensor format. It is NOT loadable by stock llama.cpp, Ollama, LM Studio, or any standard GGUF runtime. It runs only in the charlie12345/rocmfp4-llama fork. ROCmFP4 is a custom Codebook10 / finite-UE4M3 layout — it is not MXFP4 or NVFP4.

What's in this repo

File	Size	Format	BPW
`FastContext-4B-ROCmFP4-STRIX_LEAN.gguf`	2.05 GiB	`Q4_0_ROCMFP4_STRIX_LEAN`	4.38

STRIX_LEAN is a tensor-aware preset: norms stay f32, sensitive tensors keep higher precision, and the bulk of the weights use the dual/fast ROCmFP4 layouts.

Why ROCmFP4 here

On Strix Halo, token generation is memory-bandwidth-bound, so 4-bit weights decode much faster than BF16 while keeping quality intact for tool-calling.

Performance (`llama-bench`, ROCm0, FlashAttention on, Radeon 8060S)

Metric	BF16 source	ROCmFP4 STRIX_LEAN	Δ
Size	7.49 GiB	2.05 GiB	3.65× smaller
Prefill `pp512`	2388 t/s	2244 t/s	~same (compute-bound)
Decode `tg128`	25.6 t/s	73.7 t/s	2.88× faster

Tool-calling quality (`server-test-function-call.py`, 5 multi-turn cases, greedy `temp 0`)

	BF16 source	ROCmFP4 STRIX_LEAN
Cases passed	2/5	4/5

In every case both models selected and ordered the correct tools — the only failures were "no final summary produced" after correct tool use, a stopping quirk shared by the BF16 source (not a quantization artifact). Takeaway: FP4 introduced no measurable tool-calling regression. A 5-case harness can't rank models finely, so read this as "quality preserved," not "FP4 > BF16."

How to run

Build the fork for your AMD GPU (see its README), then:

HSA_OVERRIDE_GFX_VERSION=11.5.1 \
GGML_HIP_ENABLE_UNIFIED_MEMORY=1 \
./build-strix-rocmfp4/bin/llama-server \
  -m FastContext-4B-ROCmFP4-STRIX_LEAN.gguf \
  -dev ROCm0 -ngl 999 -c 262144 -fa on --jinja

For scripted/non-interactive generation use llama-completion (this fork's llama-cli is interactive-only and rejects -no-cnv). FastContext supports up to 262K context.

How it was made

# 1. HF safetensors -> BF16 GGUF
python convert_hf_to_gguf.py ./FastContext-1.0-4B-SFT --outtype bf16 --outfile fc-bf16.gguf
# 2. BF16 -> ROCmFP4 (same fork binary the server uses)
llama-quantize fc-bf16.gguf FastContext-4B-ROCmFP4-STRIX_LEAN.gguf Q4_0_ROCMFP4_STRIX_LEAN

License & attribution

Weights derive from microsoft/FastContext-1.0-4B-SFT — MIT.
Backbone: Qwen/Qwen3-4B-Instruct-2507 — Apache-2.0.
Quantization format & tooling: charlie12345/rocmfp4-llama.

This repository redistributes a quantized derivative under the terms of the upstream MIT license.

About hal0ai

Built and benchmarked with hal0ai — local-first AI agent infrastructure tuned for AMD Strix Halo. The amd-strix-halo-toolboxes ship ready-to-run ROCm + ROCmFP4 container images so you can quantize and serve large models on a single unified-memory APU. If you're running agents on AMD silicon, come say hi. 👋

A note from the author 🙇

This is my first time doing any kind of custom model quantization or training — this release is very much a learning project. So if you spot something I got wrong, or have tips on presets, calibration, or quality testing, I'd genuinely appreciate the feedback — open a Community discussion and let me know.

I made this to run as a slot in hal0, alongside the main agent — a small, fast repository-exploration subagent that ROCmFP4 lets me keep resident on the Strix Halo without crowding out the bigger models sharing the same unified memory.

If you're tinkering with local agents on AMD hardware, come check out hal0 — would love to see what you build. 🙂

Downloads last month: 192

GGUF

Model size

4B params

Architecture

qwen3

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Model tree for Hal0ai/FastContext-Hal0-4B-ROCmFP4

Base model

Qwen/Qwen3-4B-Instruct-2507

Finetuned

microsoft/FastContext-1.0-4B-SFT

Quantized

(25)

this model