Instructions to use tarruda/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 tarruda/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 tarruda/Qwen3.8-Flash-Next-GGUF:IQ4_NL
# Run inference directly in the terminal:
llama cli -hf tarruda/Qwen3.8-Flash-Next-GGUF:IQ4_NL

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf tarruda/Qwen3.8-Flash-Next-GGUF:IQ4_NL
# Run inference directly in the terminal:
llama cli -hf tarruda/Qwen3.8-Flash-Next-GGUF:IQ4_NL

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 tarruda/Qwen3.8-Flash-Next-GGUF:IQ4_NL
# Run inference directly in the terminal:
./llama-cli -hf tarruda/Qwen3.8-Flash-Next-GGUF:IQ4_NL

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 tarruda/Qwen3.8-Flash-Next-GGUF:IQ4_NL
# Run inference directly in the terminal:
./build/bin/llama-cli -hf tarruda/Qwen3.8-Flash-Next-GGUF:IQ4_NL

Use Docker

docker model run hf.co/tarruda/Qwen3.8-Flash-Next-GGUF:IQ4_NL

LM Studio
Jan

vLLM

How to use tarruda/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 "tarruda/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": "tarruda/Qwen3.8-Flash-Next-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/tarruda/Qwen3.8-Flash-Next-GGUF:IQ4_NL

Ollama
How to use tarruda/Qwen3.8-Flash-Next-GGUF with Ollama:
```
ollama run hf.co/tarruda/Qwen3.8-Flash-Next-GGUF:IQ4_NL
```
Unsloth Desktop

How to use tarruda/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 tarruda/Qwen3.8-Flash-Next-GGUF:IQ4_NL

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": "tarruda/Qwen3.8-Flash-Next-GGUF:IQ4_NL"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use tarruda/Qwen3.8-Flash-Next-GGUF with Docker Model Runner:
```
docker model run hf.co/tarruda/Qwen3.8-Flash-Next-GGUF:IQ4_NL
```

Lemonade

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

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull tarruda/Qwen3.8-Flash-Next-GGUF:IQ4_NL

Run and chat with the model

lemonade run user.Qwen3.8-Flash-Next-GGUF-IQ4_NL

List all available models

lemonade list

Hermes Agent

How to use tarruda/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 tarruda/Qwen3.8-Flash-Next-GGUF:IQ4_NL

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 tarruda/Qwen3.8-Flash-Next-GGUF:IQ4_NL

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use tarruda/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 tarruda/Qwen3.8-Flash-Next-GGUF:IQ4_NL

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 "tarruda/Qwen3.8-Flash-Next-GGUF:IQ4_NL" \
  --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

Experimental GGUFs for Qwen/Qwen3.8-Flash-Next that use split ngram out of the main weights and allow keeping it on the SSD.

These files require my metal-qwen4exp-split-ngram llama.cpp branch, which adds Qwen 3.8 Flash Next support, optimizations for Apple silicon, and MTP.

Note that this is just an experiment and these weights will likely be deleted later as llama.cpp probably won't support split ngram GGUF.

llama-server example

Run this from the downloaded repository directory. Set LLAMA_SERVER if the experimental binary is not on PATH.

#!/bin/sh
set -eu

model_dir=${MODEL_DIR:-.}
llama_server=${LLAMA_SERVER:-llama-server}

model=${MODEL:-"$model_dir/IQ4_NL/Qwen3.8-Flash-Next-IQ4_NL-00001-of-00003.gguf"}
ngram=${NGRAM_MODEL:-"$model_dir/Qwen3.8-Flash-Next-ngram-IQ4_NL.gguf"}
mtp=${MTP_MODEL:-"$model_dir/Qwen3.8-Flash-Next-MTP-Q8_0.gguf"}
mmproj=${MMPROJ_MODEL:-"$model_dir/Qwen3.8-Flash-Next-mmproj-Q8_0.gguf"}
ngram_load_mode=${NGRAM_LOAD_MODE:-resident}

exec "$llama_server" \
  --load-mode none --no-warmup \
  --model "$model" \
  --model-ngram "$ngram" --ngram-load-mode "$ngram_load_mode" \
  --model-draft "$mtp" --spec-type draft-mtp \
  --mmproj "$mmproj" \
  --ctx-size 262144 -np 1 \
  --temp 1.0 --top-p 0.95 --top-k 20 --min-p 0.0 \
  --repeat-penalty 1.0 --presence-penalty 0.0 \
  --port 8080

The example loads the complete PLE table into RAM. Set NGRAM_LOAD_MODE=read to keep it on SSD and read selected rows on demand.

Downloads last month: -

GGUF

Model size

51B params

Architecture

qwen4exp

Hardware compatibility

4-bit

5-bit

6-bit

8-bit

View +1 variant

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

Base model

Qwen/Qwen3.8-Flash-Next

Quantized

(91)

this model