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"

MTP Issues with the Q4_K_M Quant

#21

by tanpurohit26 - opened 6 days ago

Discussion

tanpurohit26

6 days ago

•

edited 6 days ago

Running the Q4_K_M (4.27BPW) model locally but the latest fork for llama.cpp does not seem to support the MTP head from Unsloth (it worked inside Unsloth Studio itself, not on the latest llama.cpp build - version: 0.4.0-dev (build 10837, commit 5202104b5). Can anyone tell me how to make it work?

The command I am using is this -

~~/llama.cpp/build/bin/llama-server \ -m "/home/[~~]/Local Models/AtomicChat/Qwen3.8-Flash-Next-AD-4.27bpw-Q4_K_M-M64/Qwen3.8-Flash-Next-AD-4.27bpw-Q4_K_M-M64-00001-of-00033.gguf" \ --mmproj "/home/[]/Local Models/AtomicChat/Qwen3.8-Flash-Next-AD-4.27bpw-Q4_K_M-M64/mmproj-Qwen3.8-Flash-Next-F16.gguf" \ --alias qwen3.8-flash-next \ -c 180000 \ -ngl 99 \ --n-cpu-moe 36 \ -fit off \ --jinja \ --flash-attn on \ --cache-type-k q8_0 --cache-type-v q8_0 \ -t 8 \ --host 127.0.0.1 --port 8081 \ --cont-batching -np 1 \ --temp 1.0 --top-p 0.95 --top-k 20 --min-p 0.0 --chat-template-file /home/[]/qwen38-template.jinja

tanpurohit26 changed discussion status to closed 6 days ago

tanpurohit26 changed discussion status to open 6 days ago

TAOTAO777

6 days ago

•

edited 6 days ago

llama.cpp original master haven't merge qwen 4 architecture mtp layer yet,if you want use mtp,you need go https://github.com/unslothai/llama.cpp use his branch and download one of mtp draft in https://huggingface.co/unsloth/Qwen3.8-Flash-Next-GGUF/tree/main/MTP,need additional VRAM/RAM,
startup code etc:
$md = "C:\Users\momori\Downloads\Qwen3.8-27B-DFlash2-Q4_K_M.gguf"
$model = "E:\Qwen3.8-Flash-Next-UD-IQ4_XS-00001-of-00003.gguf"
Start-Process -FilePath $exe -ArgumentList @(
"-md", $md,
"-m", $model,
"-c", "80000",
"--flash-attn", "on",
"--temp", "0.6",
"--top-p", "0.95",
"--top-k", "40",
"--min-p", "0.01",
"--repeat-penalty", "1.02",
"--presence-penalty", "0.0"
"-ctk", "q4_0", "-ctv", "q4_0",
"--batch-size", "400",
"--ubatch-size", "200",
"--threads", "24",
"--api-key", "123456",
"-rea", "on",
"--jinja",
"--cache-ram", "4000",
"--parallel", "1",
"--kv-unified",
"--no-warmup",
"--spec-type", "draft-mtp",
"--spec-draft-n-max", "5",
"--spec-draft-p-min", "0.84",
"--chat-template-file", $tpl,
"--load-mode", "mmap",
"--reasoning-preserve",
"--reasoning-format", "deepseek",
"--lazy-mode", "on",
"--reasoning-effort", "medium",
)

cr404

about 4 hours ago

also MTP benefits from a higher batch size value. try 2048 or even 4096 if you got the VRAM space. Try different values for spec-draft-n-max and watch the draft acceptance in the log. (higher is better, aim for at least 0.75 average acceptance)

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