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

Use Docker

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

LM Studio
Jan

vLLM

How to use DhruvalLabs/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 "DhruvalLabs/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": "DhruvalLabs/Qwen3.8-Flash-Next-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

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

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

How to use DhruvalLabs/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 DhruvalLabs/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": "DhruvalLabs/Qwen3.8-Flash-Next-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

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

Lemonade

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

Pull the model

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

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use DhruvalLabs/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 DhruvalLabs/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 "DhruvalLabs/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"

Qwen3.8-Flash-Next — GGUF Quantizations

Quantized GGUF versions of Qwen3.8-Flash-Next

Works with llama.cpp · Ollama · LM Studio

⚡ The Model Architecture

Qwen3.8-Flash-Next is an incredibly powerful 125B parameter Mixture-of-Experts (MoE) model featuring a massive 51B N-gram embedding table. Despite its massive total size, its sparse architecture only activates ~6B parameters per token, making it blazingly fast during inference!

This GGUF was quantized to Q4_K_M to preserve maximum intelligence while shrinking the massive 360GB original size down to a highly efficient 111GB footprint.

📦 Available Files (Sharded)

Because this model is so large, the Q4_K_M GGUF has been split into 3 shards to bypass the 50GB file size limit.

Filename	Size	RAM Required	Quant	Quality
`Qwen3.8-Flash-Next-Q4_K_M-00001-of-00003.gguf`	45.0 GB	-	`Q4_K_M`	⭐⭐⭐⭐
`Qwen3.8-Flash-Next-Q4_K_M-00002-of-00003.gguf`	45.0 GB	-	`Q4_K_M`	⭐⭐⭐⭐
`Qwen3.8-Flash-Next-Q4_K_M-00003-of-00003.gguf`	21.0 GB	-	`Q4_K_M`	⭐⭐⭐⭐

⚠️ IMPORTANT: You must download all 3 files into the same folder! When loading the model in llama.cpp or Ollama, simply point the program to the first file (...00001-of-00003.gguf) and it will automatically detect and stitch together the rest of the shards during inference.

(System RAM Warning: You will need at least 128GB of Unified Memory (Mac) or System RAM/VRAM to run this model without severe swapping).

🚀 How to Use

llama.cpp CLI

Make sure all 3 shards are in the same directory.

./llama-cli \
  -m Qwen3.8-Flash-Next-Q4_K_M-00001-of-00003.gguf \
  -p "Explain the benefits of sparse Mixture-of-Experts architectures." \
  --conversation \
  -n 1024

Downloads last month: 174

GGUF

Model size

177B params

Architecture

qwen4exp

Hardware compatibility

4-bit

Model tree for DhruvalLabs/Qwen3.8-Flash-Next-GGUF

Base model

Qwen/Qwen3.8-Flash-Next

Quantized

(171)

this model