Instructions to use kingjones777/Qwen3.8-Flash-Next-ROCmFP4-STRIX-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/Qwen3.8-Flash-Next-ROCmFP4-STRIX-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/Qwen3.8-Flash-Next-ROCmFP4-STRIX-GGUF:Q4_0
# Run inference directly in the terminal:
llama cli -hf kingjones777/Qwen3.8-Flash-Next-ROCmFP4-STRIX-GGUF:Q4_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf kingjones777/Qwen3.8-Flash-Next-ROCmFP4-STRIX-GGUF:Q4_0
# Run inference directly in the terminal:
llama cli -hf kingjones777/Qwen3.8-Flash-Next-ROCmFP4-STRIX-GGUF:Q4_0

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/Qwen3.8-Flash-Next-ROCmFP4-STRIX-GGUF:Q4_0
# Run inference directly in the terminal:
./llama-cli -hf kingjones777/Qwen3.8-Flash-Next-ROCmFP4-STRIX-GGUF:Q4_0

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/Qwen3.8-Flash-Next-ROCmFP4-STRIX-GGUF:Q4_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf kingjones777/Qwen3.8-Flash-Next-ROCmFP4-STRIX-GGUF:Q4_0

Use Docker

docker model run hf.co/kingjones777/Qwen3.8-Flash-Next-ROCmFP4-STRIX-GGUF:Q4_0

LM Studio
Jan

vLLM

How to use kingjones777/Qwen3.8-Flash-Next-ROCmFP4-STRIX-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kingjones777/Qwen3.8-Flash-Next-ROCmFP4-STRIX-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/Qwen3.8-Flash-Next-ROCmFP4-STRIX-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/kingjones777/Qwen3.8-Flash-Next-ROCmFP4-STRIX-GGUF:Q4_0

Ollama
How to use kingjones777/Qwen3.8-Flash-Next-ROCmFP4-STRIX-GGUF with Ollama:
```
ollama run hf.co/kingjones777/Qwen3.8-Flash-Next-ROCmFP4-STRIX-GGUF:Q4_0
```
Unsloth Desktop

How to use kingjones777/Qwen3.8-Flash-Next-ROCmFP4-STRIX-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/Qwen3.8-Flash-Next-ROCmFP4-STRIX-GGUF:Q4_0

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/Qwen3.8-Flash-Next-ROCmFP4-STRIX-GGUF:Q4_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use kingjones777/Qwen3.8-Flash-Next-ROCmFP4-STRIX-GGUF with Docker Model Runner:
```
docker model run hf.co/kingjones777/Qwen3.8-Flash-Next-ROCmFP4-STRIX-GGUF:Q4_0
```

Lemonade

How to use kingjones777/Qwen3.8-Flash-Next-ROCmFP4-STRIX-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull kingjones777/Qwen3.8-Flash-Next-ROCmFP4-STRIX-GGUF:Q4_0

Run and chat with the model

lemonade run user.Qwen3.8-Flash-Next-ROCmFP4-STRIX-GGUF-Q4_0

List all available models

lemonade list

Hermes Agent

How to use kingjones777/Qwen3.8-Flash-Next-ROCmFP4-STRIX-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/Qwen3.8-Flash-Next-ROCmFP4-STRIX-GGUF:Q4_0

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/Qwen3.8-Flash-Next-ROCmFP4-STRIX-GGUF:Q4_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use kingjones777/Qwen3.8-Flash-Next-ROCmFP4-STRIX-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/Qwen3.8-Flash-Next-ROCmFP4-STRIX-GGUF:Q4_0

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/Qwen3.8-Flash-Next-ROCmFP4-STRIX-GGUF:Q4_0" \
  --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"

Why is not 256k at full context?

by qZitronen - opened 3 days ago

Discussion

qZitronen

3 days ago

Your text says your test was at 131,072 context max, why not measure at 256k as well?

kingjones777

Owner 3 days ago

•

edited 3 days ago

Good catch — that's my test design showing, not a ceiling. I ran the ladder at 8k/32k/64k/128k and stopped at 128k because that's where I set the top rung, not because anything failed. The model's native max is 262,144 and I simply hadn't measured it.

Worth saying why I expect it to fit: GTT at load only went 63.3 → 67.2 GiB across that whole ladder — 3.9 GiB for 16× the context. QSA's 512-block / 2048-token budget means KV barely grows here, unlike a conventional model where 128k of KV costs tens of GiB. Extrapolating that curve, 262k should sit around 71 GiB on a 128 GB box.

I'm running 262,144 now and I'll put the real numbers on the cards — including if it doesn't fit, because "the ladder stopped here" and "the hardware stops here" are different claims and I shouldn't have let the card blur them.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment