Instructions to use kingjones777/Llama-4-Scout-17B-16E-Instruct-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/Llama-4-Scout-17B-16E-Instruct-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/Llama-4-Scout-17B-16E-Instruct-ROCmFP4-GGUF:Q4_0_ROCMFP
# Run inference directly in the terminal:
llama cli -hf kingjones777/Llama-4-Scout-17B-16E-Instruct-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/Llama-4-Scout-17B-16E-Instruct-ROCmFP4-GGUF:Q4_0_ROCMFP
# Run inference directly in the terminal:
llama cli -hf kingjones777/Llama-4-Scout-17B-16E-Instruct-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/Llama-4-Scout-17B-16E-Instruct-ROCmFP4-GGUF:Q4_0_ROCMFP
# Run inference directly in the terminal:
./llama-cli -hf kingjones777/Llama-4-Scout-17B-16E-Instruct-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/Llama-4-Scout-17B-16E-Instruct-ROCmFP4-GGUF:Q4_0_ROCMFP
# Run inference directly in the terminal:
./build/bin/llama-cli -hf kingjones777/Llama-4-Scout-17B-16E-Instruct-ROCmFP4-GGUF:Q4_0_ROCMFP

Use Docker

docker model run hf.co/kingjones777/Llama-4-Scout-17B-16E-Instruct-ROCmFP4-GGUF:Q4_0_ROCMFP

LM Studio
Jan

vLLM

How to use kingjones777/Llama-4-Scout-17B-16E-Instruct-ROCmFP4-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kingjones777/Llama-4-Scout-17B-16E-Instruct-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/Llama-4-Scout-17B-16E-Instruct-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/Llama-4-Scout-17B-16E-Instruct-ROCmFP4-GGUF:Q4_0_ROCMFP

Ollama
How to use kingjones777/Llama-4-Scout-17B-16E-Instruct-ROCmFP4-GGUF with Ollama:
```
ollama run hf.co/kingjones777/Llama-4-Scout-17B-16E-Instruct-ROCmFP4-GGUF:Q4_0_ROCMFP
```
Unsloth Desktop

How to use kingjones777/Llama-4-Scout-17B-16E-Instruct-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/Llama-4-Scout-17B-16E-Instruct-ROCmFP4-GGUF:Q4_0_ROCMFP

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:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "kingjones777/Llama-4-Scout-17B-16E-Instruct-ROCmFP4-GGUF:Q4_0_ROCMFP"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use kingjones777/Llama-4-Scout-17B-16E-Instruct-ROCmFP4-GGUF with Docker Model Runner:
```
docker model run hf.co/kingjones777/Llama-4-Scout-17B-16E-Instruct-ROCmFP4-GGUF:Q4_0_ROCMFP
```

Lemonade

How to use kingjones777/Llama-4-Scout-17B-16E-Instruct-ROCmFP4-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull kingjones777/Llama-4-Scout-17B-16E-Instruct-ROCmFP4-GGUF:Q4_0_ROCMFP

Run and chat with the model

lemonade run user.Llama-4-Scout-17B-16E-Instruct-ROCmFP4-GGUF-Q4_0_ROCMFP

List all available models

lemonade list

Hermes Agent

How to use kingjones777/Llama-4-Scout-17B-16E-Instruct-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/Llama-4-Scout-17B-16E-Instruct-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/Llama-4-Scout-17B-16E-Instruct-ROCmFP4-GGUF:Q4_0_ROCMFP

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use kingjones777/Llama-4-Scout-17B-16E-Instruct-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/Llama-4-Scout-17B-16E-Instruct-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/Llama-4-Scout-17B-16E-Instruct-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"

⚠️ STOCK llama.cpp WILL NOT LOAD THIS MODEL

Q4_0_ROCMFP4_COHERENT (ftype 102) exists only in charlie12345/ROCmFPX. Stock llama.cpp reports invalid ggml type. Ignore the auto-generated "Use this model" commands above.

⚠️ -fa off is required — flash attention breaks the vision path on gfx1151.

56.98 GiB · 17.72 tok/s on a Ryzen AI MAX+ 395 (Strix Halo, gfx1151).

Llama-4-Scout-17B-16E-Instruct — ROCmFP4 (tier 102 `COHERENT`) GGUF

The first ROCmFP4 build of Llama 4 Scout. 109B total / 17B active MoE with vision, quantized for AMD gfx1151 (Ryzen AI MAX+ 395 / Strix Halo).


File	`Llama-4-Scout-17B-16E-Instruct-Q4_0_ROCMFP4_COHERENT.gguf`
Size	56.98 GiB (61,182,279,392 B)
BPW	4.54
ftype	`Q4_0_ROCMFP4_COHERENT` (102)
Tensors	628 · 480 at `q4_0_rocmfp4`
Architecture	48 layers · hidden 5120 · 16 experts, 1 active/token · vision patch 14

Quantized from unsloth's BF16 GGUF (200.8 GiB, 5 shards, byte-verified against the Hub) — a lossless source, not a requantization and not our own re-conversion.

Recipe

--output-tensor-type q6_K --token-embedding-type q6_K   ...   Q4_0_ROCMFP4_COHERENT 16

⭐ --output-tensor-type q6_K is what actually protects the LM head — the COHERENT tier alone still leaves output.weight at 4-bit. Audited in the finished file: output.weight q6_K, token_embd.weight q6_K.

Measured

Ryzen AI MAX+ 395, gfx1151, ROCm. -ngl 999 -c 4096 -fa off -fit off --mmproj. Median of 3, warm-up discarded, otherwise-idle box.


Decode	17.72 tok/s (17.69 / 17.72 / 17.74 — tight)
Load	48 s cold, 22 s warm

Correctness (max_tokens: 1024): 17×23 ⇒ ✅ 391 · capital of Japan ⇒ ✅ Tokyo · days in 2024 ⇒ ✅ 366

Vision (-fa off + bundled BF16 mmproj):

image	result
256×256 solid red	✅ `Red.`
256×256 shapes	✅ red square · green circle · blue triangle · yellow border · black background
512×512	⛔ `failed to encode image slice` — server dies

⚠️ Use images at or near 256×256. 512×512 fails to encode on this build. The projector is fine — 256×256 reads colour and shape and spatial layout correctly — but larger images hit an encode-slice limit. Resize before sending.

No draft head. This model ships no MTP/EAGLE/nextn tensors (common_speculative_init: no implementations specified), so there is no speculative-decoding speedup to enable and no acceptance-length figure to quote.

What was NOT measured

No perplexity run, and no quality A/B against the BF16 source.
No long-context testing. · No tool-calling evaluation.
Vision was smoke-tested on synthetic images only — no vision benchmark.

Base model licence (Llama 4 Community License) inherited; all credit for the weights goes to Meta.

Downloads last month: 170

GGUF

Model size

108B params

Architecture

llama4

Hardware compatibility

4-bit

Model tree for kingjones777/Llama-4-Scout-17B-16E-Instruct-ROCmFP4-GGUF

Base model

meta-llama/Llama-4-Scout-17B-16E

Finetuned

meta-llama/Llama-4-Scout-17B-16E-Instruct

Quantized

(39)

this model

kingjones777
/

Llama-4-Scout-17B-16E-Instruct-ROCmFP4-GGUF

⚠️ STOCK `llama.cpp` WILL NOT LOAD THIS MODEL

Llama-4-Scout-17B-16E-Instruct — ROCmFP4 (tier 102 `COHERENT`) GGUF

Recipe

Measured

What was NOT measured

Model tree for kingjones777/Llama-4-Scout-17B-16E-Instruct-ROCmFP4-GGUF

⚠️ STOCK llama.cpp WILL NOT LOAD THIS MODEL

Llama-4-Scout-17B-16E-Instruct — ROCmFP4 (tier 102 COHERENT) GGUF

Recipe

Measured

What was NOT measured

Model tree for kingjones777/Llama-4-Scout-17B-16E-Instruct-ROCmFP4-GGUF

⚠️ STOCK `llama.cpp` WILL NOT LOAD THIS MODEL

Llama-4-Scout-17B-16E-Instruct — ROCmFP4 (tier 102 `COHERENT`) GGUF