Instructions to use kingjones777/Qwen3.5-0.8B-ROCmFP4-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use kingjones777/Qwen3.5-0.8B-ROCmFP4-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 kingjones777/Qwen3.5-0.8B-ROCmFP4-GGUF:Q4_0_ROCMFP
# Run inference directly in the terminal:
llama cli -hf kingjones777/Qwen3.5-0.8B-ROCmFP4-GGUF:Q4_0_ROCMFP

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf kingjones777/Qwen3.5-0.8B-ROCmFP4-GGUF:Q4_0_ROCMFP
# Run inference directly in the terminal:
llama cli -hf kingjones777/Qwen3.5-0.8B-ROCmFP4-GGUF:Q4_0_ROCMFP

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 kingjones777/Qwen3.5-0.8B-ROCmFP4-GGUF:Q4_0_ROCMFP
# Run inference directly in the terminal:
./llama-cli -hf kingjones777/Qwen3.5-0.8B-ROCmFP4-GGUF:Q4_0_ROCMFP

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 kingjones777/Qwen3.5-0.8B-ROCmFP4-GGUF:Q4_0_ROCMFP
# Run inference directly in the terminal:
./build/bin/llama-cli -hf kingjones777/Qwen3.5-0.8B-ROCmFP4-GGUF:Q4_0_ROCMFP

Use Docker

docker model run hf.co/kingjones777/Qwen3.5-0.8B-ROCmFP4-GGUF:Q4_0_ROCMFP

LM Studio
Jan

vLLM

How to use kingjones777/Qwen3.5-0.8B-ROCmFP4-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kingjones777/Qwen3.5-0.8B-ROCmFP4-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": "kingjones777/Qwen3.5-0.8B-ROCmFP4-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/kingjones777/Qwen3.5-0.8B-ROCmFP4-GGUF:Q4_0_ROCMFP

Ollama
How to use kingjones777/Qwen3.5-0.8B-ROCmFP4-GGUF with Ollama:
```
ollama run hf.co/kingjones777/Qwen3.5-0.8B-ROCmFP4-GGUF:Q4_0_ROCMFP
```

Unsloth Studio

How to use kingjones777/Qwen3.5-0.8B-ROCmFP4-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 kingjones777/Qwen3.5-0.8B-ROCmFP4-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 kingjones777/Qwen3.5-0.8B-ROCmFP4-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for kingjones777/Qwen3.5-0.8B-ROCmFP4-GGUF to start chatting

How to use kingjones777/Qwen3.5-0.8B-ROCmFP4-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf kingjones777/Qwen3.5-0.8B-ROCmFP4-GGUF:Q4_0_ROCMFP

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": "kingjones777/Qwen3.5-0.8B-ROCmFP4-GGUF:Q4_0_ROCMFP"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use kingjones777/Qwen3.5-0.8B-ROCmFP4-GGUF with Docker Model Runner:
```
docker model run hf.co/kingjones777/Qwen3.5-0.8B-ROCmFP4-GGUF:Q4_0_ROCMFP
```

Lemonade

How to use kingjones777/Qwen3.5-0.8B-ROCmFP4-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull kingjones777/Qwen3.5-0.8B-ROCmFP4-GGUF:Q4_0_ROCMFP

Run and chat with the model

lemonade run user.Qwen3.5-0.8B-ROCmFP4-GGUF-Q4_0_ROCMFP

List all available models

lemonade list

Hermes Agent

How to use kingjones777/Qwen3.5-0.8B-ROCmFP4-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 kingjones777/Qwen3.5-0.8B-ROCmFP4-GGUF:Q4_0_ROCMFP

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 kingjones777/Qwen3.5-0.8B-ROCmFP4-GGUF:Q4_0_ROCMFP

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use kingjones777/Qwen3.5-0.8B-ROCmFP4-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf kingjones777/Qwen3.5-0.8B-ROCmFP4-GGUF:Q4_0_ROCMFP

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 "kingjones777/Qwen3.5-0.8B-ROCmFP4-GGUF:Q4_0_ROCMFP" \
  --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"

Qwen3.5-0.8B — ROCmFP4 / ROCmFPX GGUF

First ROCmFP4/ROCmFPX quantization of Qwen/Qwen3.5-0.8B. Four quants, built from the Hub BF16 GGUF (no re-conversion), each individually verified on real hardware.

Built for AMD Strix Halo (gfx1151) — Ryzen AI MAX+ 395, 128 GB unified — with the ROCmFPX llama.cpp fork.

⚠️ Needs a ROCmFPX-capable llama.cpp build. These will not load in stock llama.cpp / Ollama / LM Studio.

Variants

file	ftype	size	`token_embd`	decode	correctness
`Qwen3.5-0.8B-Q4_0_ROCMFP4_COHERENT.gguf`	102	0.47 GiB	Q6_K	171.38 t/s	2/3
`Qwen3.5-0.8B-Q6_0_ROCMFPX_AGENT.gguf`	114	0.68 GiB	Q8_0	138.81 t/s	3/3
`Qwen3.5-0.8B-Q8_0_ROCMFPX.gguf`	111	0.74 GiB	Q8_0	142.38 t/s	2/3
`Qwen3.5-0.8B-Q8_0_ROCMFPX_AGENT.gguf`	115	0.75 GiB	Q8_0	142.3 t/s	2/3

mmproj-BF16.gguf is included — required for image input (-fa off).

Which to pick: the 4-bit (102) — fastest and smallest, same answers as the 8-bits.

⚠️ Q6_0_ROCMFPX_AGENT (114) is the weakest choice here: larger than the 4-bit and slower than the plain 8-bit. The AGENT recipe raises speculative-draft acceptance, and Qwen3.5-0.8B ships no drafter, so that benefit cannot apply. It is included for completeness.

⚠️ Read this before deploying the 0.8B

On some prompts this model never emits a final answer — it continues reasoning until it hits the token limit. Measured on the plain 8-bit with the question "How many days were there in the year 2024?":

max_tokens	finish_reason	reasoning length
1024	`length`	2,521 chars
2048	`length`	4,882
4096	`length`	9,595
8000	`length`	18,588

Eight times the budget produced eight times the reasoning and still no answer. This is not quantization damage — the BF16 source behaves identically, and the 6-bit build happens to answer the same question fine. It is the model at this size failing to terminate its own chain of thought.

Practical impact: you will see empty responses (content: "", finish_reason: "length"), not wrong ones. If you deploy this, handle empty content explicitly, and consider constraining or disabling the thinking template for short factual queries.

The correctness scores in the table above are measured with max_tokens: 1024 and count a non-terminating answer as a miss.

Measured — not estimated

Hardware: Ryzen AI MAX+ 395 (Strix Halo, gfx1151), 128 GB unified. -ngl 999 -c 4096 -fa on -fit off. 300 tokens, warm-up discarded, median of 3.

ftype	run 1 / 2 / 3	median	spread
102	171.75 171.38 171.15	171.38	1.004
114	139.27 138.81 138.7	138.81	1.004
111	142.38 142.38 142.26	142.38	1.001
115	142.46 142.3 141.95	142.3	1.004

No MTP/EAGLE drafter ships with this model, so these are the deployed numbers with nothing left on the table.

Head protection

Qwen3.5-0.8B has tied embeddings — there is no output.weight tensor, so --output-tensor-type is a silent no-op and --token-embedding-type is the only flag that protects the head. Audited by exact tensor name on every artifact.

    501452832  Qwen3.5-0.8B-Q4_0_ROCMFP4_COHERENT.gguf
    734920736  Qwen3.5-0.8B-Q6_0_ROCMFPX_AGENT.gguf
    796293152  Qwen3.5-0.8B-Q8_0_ROCMFPX.gguf
    804321312  Qwen3.5-0.8B-Q8_0_ROCMFPX_AGENT.gguf