Instructions to use unsloth/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 unsloth/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 unsloth/Qwen3.8-Flash-Next-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama cli -hf unsloth/Qwen3.8-Flash-Next-GGUF:UD-Q4_K_XL

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf unsloth/Qwen3.8-Flash-Next-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama cli -hf unsloth/Qwen3.8-Flash-Next-GGUF:UD-Q4_K_XL

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf unsloth/Qwen3.8-Flash-Next-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./build/bin/llama cli -hf unsloth/Qwen3.8-Flash-Next-GGUF:UD-Q4_K_XL

Use Docker

docker model run hf.co/unsloth/Qwen3.8-Flash-Next-GGUF:UD-Q4_K_XL

Llama new
LM Studio
Jan

vLLM

How to use unsloth/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 "unsloth/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": "unsloth/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/unsloth/Qwen3.8-Flash-Next-GGUF:UD-Q4_K_XL

Ollama
How to use unsloth/Qwen3.8-Flash-Next-GGUF with Ollama:
```
ollama run hf.co/unsloth/Qwen3.8-Flash-Next-GGUF:UD-Q4_K_XL
```
Unsloth Desktop

How to use unsloth/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 unsloth/Qwen3.8-Flash-Next-GGUF:UD-Q4_K_XL

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": "unsloth/Qwen3.8-Flash-Next-GGUF:UD-Q4_K_XL"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use unsloth/Qwen3.8-Flash-Next-GGUF with Docker Model Runner:
```
docker model run hf.co/unsloth/Qwen3.8-Flash-Next-GGUF:UD-Q4_K_XL
```

Lemonade

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

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull unsloth/Qwen3.8-Flash-Next-GGUF:UD-Q4_K_XL

Run and chat with the model

lemonade run user.Qwen3.8-Flash-Next-GGUF-UD-Q4_K_XL

List all available models

lemonade list

Hermes Agent

How to use unsloth/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 unsloth/Qwen3.8-Flash-Next-GGUF:UD-Q4_K_XL

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 unsloth/Qwen3.8-Flash-Next-GGUF:UD-Q4_K_XL

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use unsloth/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 unsloth/Qwen3.8-Flash-Next-GGUF:UD-Q4_K_XL

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 "unsloth/Qwen3.8-Flash-Next-GGUF:UD-Q4_K_XL" \
  --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"

New discussion

Resources

View closed (13)

How can I improve the prefilling speed for this model?

#49 opened 2 months ago by

BipedalBit

Getting 10+ tok/s on a 3060 laptop with 48GB RAM

🔥 12

#48 opened 2 months ago by

2vibeornot2vibe

context type MTP requested but model doesn't contain MTP layers

👀 4

#47 opened 2 months ago by

Manhandle6292

Is it possible to run it with a combined memory setup: 16 GB VRAM + 64 GB RAM + SSD for offloading n-grams?

#46 opened 2 months ago by

testtestad

Qwen3.8-Flash-Next on Strix Halo: ~40 tok/s code at 120K+ context

👍 9

#45 opened 2 months ago by

Engardium

Can the 51B n-gram table be kept on NVMe/SSD?

#44 opened 2 months ago by

NamerPRO

I'm a beginner, how do I use GGUF files that contain multiple files?

#43 opened 2 months ago by

jevencheung

Q4_K_XL / llama-server / Hallucination after 150k of filled context

#42 opened 2 months ago by

manisab

Works on my machine

🤯 2

#41 opened 2 months ago by

emcourtney

Qwen3.8-Flash-Next: deep-context decode slowdown + top_k crash + MTP results (3x RTX 3090, full log)

#40 opened 2 months ago by

karantula

4x slower than it should be? 🐢

🤗👀 5

#38 opened 2 months ago by

auf1r2

3060 12 gb

#37 opened 2 months ago by

deluxenew

nice work!

❤️🔥 3

#36 opened 2 months ago by

smilegirom

Is the n-gram chunk embedded in the gguf(s), and is it ~51GB independent of quantization?

#35 opened 3 months ago by

dagb

Measured: ngram-map-k beats ngram-mod; ngram-cache costs -24% on prose (5060 Ti 16GB + 128GB)

🚀👍 6

#34 opened 3 months ago by

solarkyle

Frankenstein needs help for settings

#32 opened 3 months ago by

svarognsa

Early report running it on a DGX Spark, 4 concurrent @ 256k bf16 with SSD offload

👍 7

#31 opened 3 months ago by

sleepyeldrazi

Bug: Gibberish output on Strix Halo since Unsloth Desktop sets GGML_CUDA_ENABLE_UNIFIED_MEMORY=1 on HIP build

👍 1

#30 opened 3 months ago by

adi-0

NVME vs Optane?

#29 opened 3 months ago by

AndyFaceHugger

strix halo 128gb recommendations

#28 opened 3 months ago by

dilavni

Thinking Nightmare

🧠 2

#27 opened 3 months ago by

WhiteDan64

imatrix file

#25 opened 3 months ago by

erazortt

Tested on RTX5070TI 16GB VRAM: 20 t/s

👀👍 10

#24 opened 3 months ago by

WhiteDan64

How to keep n-gram table on fast nvme ssd

#23 opened 3 months ago by

mayankiit04

Question about loading the model with RTX 4090 and RTX 6000 pro?

#22 opened 3 months ago by

LukeC110

MTP support in Q4 ?

👍 4

#21 opened 3 months ago by

dpachong

Are these quants using Unsloth UD 3.0 or 2.0?

#20 opened 3 months ago by

InfernalDread

Suggestion: Support for Ngram SSD Offloading in Unsloth Desktop

➕ 29

#15 opened 3 months ago by

wuyule

i wanted to test the new unsloth studio for this model but it hangs all the time

#13 opened 3 months ago by

Manni1000

Is it even worth trying to run the 1-bit version?

#12 opened 3 months ago by

testtestad

Is it possible to offload n-gram to an NVMe SSD?

👀🚀 31

#11 opened 3 months ago by

lingyezhixing

glm5.3 flash just relaeased

#10 opened 3 months ago by

smailimohammad

pro6000能否放得下

#9 opened 3 months ago by

Ansonvllm

Unsloth Studio vs Unsloth Desktop Day Zero Support

#8 opened 3 months ago by

Chuck572

How much VRAM do you need to run this model?

👀 1

#7 opened 3 months ago by

ntp777

UD-IQ1_S 72.5 GB, need QWEN 3.8 35B-A3B or 35B-A5B MoE

😔🔥 14

#6 opened 3 months ago by

MaxDaddyLongs

Share your model speed here

🤝 11

#3 opened 3 months ago by

anvme

NVFP4 support on day 0?

#2 opened 3 months ago by

tuanlai001

Wow!

🔥🚀 8

#1 opened 3 months ago by

anvme