unsloth
/

Qwen3.8-Flash-Next-GGUF

Image-Text-to-Text

Model card Files Files and versions

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

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
```

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

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

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"

Resources

View closed (13)

Run Qwen3.8-Flash-Next Faster with Less Thinking and Less Tokens

#96 opened 4 days ago by

Introducing Qwen3.8-Flash Unsloth Dynamic v3.1 GGUFs!

#91 opened 6 days ago by

Run 170 tokens/s Qwen3.8-Flash with MTP! ⚡

#56 opened 2 months ago by

All Qwen3.8-Flash quants are here! 🔥 Run in Unsloth Desktop!

#33 opened 3 months ago by

Fix Dynamic GGUF version

#103 opened 34 minutes ago by

IQ3_XXS is insane and probably the best size to quality ratio

#102 opened 1 day ago by

UD-IQ4_XS: canned, off-topic "graph cycle proof" reasoning replaces real thinking on agentic tool-call turns (~100K context)

#101 opened 1 day ago by

IQ2_XS vs Q2_K_XL

#100 opened 1 day ago by

Manually hex edit engram file

#99 opened 2 days ago by

Knocked it out of the park! ⚾️💨

#95 opened 4 days ago by

Qwen3.8-Flash-Next Unsloth Dynamic v3.1 on NVMe: a local 30-task A/B

#93 opened 6 days ago by

UD-Q4_K_XL: 10/10 strict-256K runs on a 24 GB card, and a chat-template note for Claude Code users

#92 opened 6 days ago by

Spelling issues on Q6_K_XL / Q5_K_XL

#89 opened 9 days ago by

Qwen3.8-Flash-Next-GGUF Unsloth Dynamic 3.0 Quants

#88 opened 11 days ago by

llama.cpp merge weights update

#87 opened 16 days ago by

UD-Q5_K_XL: shard 1 is 6 bytes short of its aligned data offset

#86 opened 22 days ago by

BF16 part 3 out of 8 is damaged, its size 102gib.

#85 opened 30 days ago by

mtp weight failed! check_tensor_dims: tensor 'token_embd.weight' not found

#84 opened about 1 month ago by

MTP benchmarks

#83 opened about 1 month ago by

A quant in between Q4_K_XL and IQ4_XS

#82 opened about 1 month ago by

Any way to separately select ngram quantization and model quantization?

#81 opened about 1 month ago by

unsloth studio vs strata engine for qwen3.8-flash-next

#80 opened about 1 month ago by

llama.cpp now supports MTP in main, but these quants don't seem compatible

#79 opened about 1 month ago by

will the new llama.cpp build 11330+ support the mtp file?

#78 opened about 1 month ago by

ud-q5_k_s or ud-q5_k_m please

#77 opened about 1 month ago by

Does this quant actually support engram SSD offload or not in llama.cpp??

#76 opened about 1 month ago by

n-gram from SSD: how exactly?

#75 opened about 2 months ago by

Running IQ4_XS with MTP , crashing after a while.

#74 opened about 2 months ago by

What is the actual difference between these two drafts? (MTP Q4_K_M | 2.79 GB) vs ( MTP Q4_K_M | 1.91 GB)

#73 opened about 2 months ago by

sarkaritamminen

[BUG / Regression] SIGABRT in build_hc_mix during MTP graph reservation for Qwen3.8-Flash-Next (qwen4exp)

#72 opened about 2 months ago by

llama cpp prebuilt 10909 and higher throw core exception

#71 opened about 2 months ago by

Are there any qualitative benchmarks between Q_8 vs. BF16?

#70 opened about 2 months ago by

单块16GB GPU + 64GB 内存：UD-IQ3_XXS（Windows）上27.5–29 tok/s — 完整指南 + 内置配置

#69 opened about 2 months ago by

Up to 34 t/s on 2× Tesla V100 16 GB + dual Xeon E5-2680 v4 (128 GB DDR4): tuning results for llama.cpp and ik_llama.cpp

#68 opened about 2 months ago by

Request: a UD quant between IQ4_XS (93.7 GB) and Q4_K_XL (111 GB) for 128 GB unified-memory machines (Strix Halo)

#67 opened 2 months ago by

UD-IQ1_M on 6GB VRAM (GTX 1660 Ti): numbers, ladder to 128k, hiccups + fixes

#66 opened 2 months ago by

Run UD-Q4-K-XL on 16GB VRAM and 32 GB RAM at 15+ tok/s

#65 opened 2 months ago by

Why are PLE/ngram weights quantized at all?

#64 opened 2 months ago by

The best model under 200B reaches near-10 exact batch throughput on one laptop CPU

#63 opened 2 months ago by

Qwen3.8-Flash-Next UD-Q2_K_XL: deterministic exact-literal truncation with contrasting long-context fidelity vs Q2_K

#62 opened 2 months ago by

Quick share: Got 30–40 t/s on the RTX 5060 Ti 16GB

#61 opened 2 months ago by

Too slow in 2 x H100, got decode 40t/s

#60 opened 2 months ago by

Small gain with MTP

#59 opened 2 months ago by

Strange URL lookup when using agentic tools with it

#58 opened 2 months ago by

Claude code cli errors out with llama.cpp

#57 opened 2 months ago by

Tested new MTP module with UD-Q4_K_XL on Pro 6000 Max-Q

#55 opened 2 months ago by

MTP loading errors with IQ3_XXS quantz

#54 opened 2 months ago by

can we have a gguf varity where ngram layer 2 is at q8?

#53 opened 2 months ago by

Qwen3.8-Flash-Next (qwen4exp) garbage output on Strix Halo (gfx1151) over ROCm 7.x - root cause and verified fix (build from PR #27941)

#52 opened 2 months ago by

Is it possible to made a GGUF without N-gram?

#51 opened 2 months ago by