Instructions to use AtomicChat/Qwen3.8-Flash-Next-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 AtomicChat/Qwen3.8-Flash-Next-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 AtomicChat/Qwen3.8-Flash-Next-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf AtomicChat/Qwen3.8-Flash-Next-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf AtomicChat/Qwen3.8-Flash-Next-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf AtomicChat/Qwen3.8-Flash-Next-GGUF:Q4_K_M

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 AtomicChat/Qwen3.8-Flash-Next-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf AtomicChat/Qwen3.8-Flash-Next-GGUF:Q4_K_M

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 AtomicChat/Qwen3.8-Flash-Next-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf AtomicChat/Qwen3.8-Flash-Next-GGUF:Q4_K_M

Use Docker

docker model run hf.co/AtomicChat/Qwen3.8-Flash-Next-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use AtomicChat/Qwen3.8-Flash-Next-GGUF with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/AtomicChat/Qwen3.8-Flash-Next-GGUF:Q4_K_M

Ollama
How to use AtomicChat/Qwen3.8-Flash-Next-GGUF with Ollama:
```
ollama run hf.co/AtomicChat/Qwen3.8-Flash-Next-GGUF:Q4_K_M
```
Unsloth Desktop

How to use AtomicChat/Qwen3.8-Flash-Next-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf AtomicChat/Qwen3.8-Flash-Next-GGUF:Q4_K_M

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": "AtomicChat/Qwen3.8-Flash-Next-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use AtomicChat/Qwen3.8-Flash-Next-GGUF with Docker Model Runner:
```
docker model run hf.co/AtomicChat/Qwen3.8-Flash-Next-GGUF:Q4_K_M
```

Lemonade

How to use AtomicChat/Qwen3.8-Flash-Next-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull AtomicChat/Qwen3.8-Flash-Next-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3.8-Flash-Next-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use AtomicChat/Qwen3.8-Flash-Next-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 AtomicChat/Qwen3.8-Flash-Next-GGUF:Q4_K_M

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 AtomicChat/Qwen3.8-Flash-Next-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use AtomicChat/Qwen3.8-Flash-Next-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf AtomicChat/Qwen3.8-Flash-Next-GGUF:Q4_K_M

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 "AtomicChat/Qwen3.8-Flash-Next-GGUF:Q4_K_M" \
  --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"

Launch command for Orin 64GB

#22

by kryll666 - opened 9 days ago

Discussion

kryll666

9 days ago

You'll need the MTP branch called qwen4exp/mtp from https://github.com/danielhanchen/llama.cpp and build it first.

Then run:

#!/bin/bash

# Resolve model path relative to this script's own directory, so it works from anywhere
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
MODEL="AtomicChat/Qwen3.8-Flash-Next-GGUF:Q4_K_M"
MMPROJ=".cache/huggingface/hub/models--AtomicChat--Qwen3.8-Flash-Next-GGUF/snapshots/142262902a46f7daed19c79d0771534c8106ad59/mmproj-Qwen3.8-Flash-Next-BF16.gguf"
# Check in unslot's huggingface repository
MPTFILE="mtp-Qwen3.8-Flash-Next-shared-Q4_K_M.gguf"
# Disabled since they burn precious memory for nothing
#   --mmproj "$MMPROJ" \
# Not worth it. Computing MTP heads on the CPU doesn't improve the inference rate
#   --spec-draft-ngl 0 \


$HOME/llama.cpp.mtp/build/bin/llama-server \
  -hf "$MODEL" \
  --no-mmproj \
  -ngl 99 \
  --n-cpu-moe 0 \
  -fa on \
  -fit off \
  --load-mode mlock \
  --parallel 1 \
  --port 8000 \
  --host 0.0.0.0 \
  --ctx-size 131072 \
  -b 4096 \
  --cache-reuse 256 \
  --ubatch-size 512 \
  --cache-type-k q4_0 \
  --cache-type-v q4_0 \
  --temp 0.7 \
  --top-p 0.90 \
  --top-k 20 \
  --min-p 0.0 \
  --presence-penalty 0.0 \
  --repeat-penalty 1.0 \
  --seed 1902 \
  --log-colors on \
  --threads 12 \
  --jinja \
  --spec-type draft-mtp \
  --model-draft "$MPTFILE" \
  --spec-draft-type-k q4_0 \
  --spec-draft-type-v q4_0 \
  --spec-draft-n-min 1 \
  --spec-draft-n-max 1 \
  --chat-template-kwargs '{"reasoning_effort":"medium"}' \
  --reasoning-preserve

I've also disabled all useless services to free as much memory are possible and I have a 8GB swap set up (but only 1GB is used in inference).
This is the best config found by (numerous) trials and a lot of errors. I'm getting ~130t/s in pp and 19 t/s in eval for what it's worth. This model is made for very very short system context.

palladium107

8 days ago

Correct me if I'm wrong but threads 12 does not make any difference, right? Because you are offloading nothing to the cpu (cpu-moe 0). In my experience if you are able to raise batch size and ubatch size you will get better tokenization performance. In a longer context I'm getting around 200-220t/s with a 5070Ti and a 3090.

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