Instructions to use meshllm/Qwen3.8-Flash-Next-UD-IQ1_S-layers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use meshllm/Qwen3.8-Flash-Next-UD-IQ1_S-layers 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 meshllm/Qwen3.8-Flash-Next-UD-IQ1_S-layers:BF16
# Run inference directly in the terminal:
llama cli -hf meshllm/Qwen3.8-Flash-Next-UD-IQ1_S-layers:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf meshllm/Qwen3.8-Flash-Next-UD-IQ1_S-layers:BF16
# Run inference directly in the terminal:
llama cli -hf meshllm/Qwen3.8-Flash-Next-UD-IQ1_S-layers:BF16

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 meshllm/Qwen3.8-Flash-Next-UD-IQ1_S-layers:BF16
# Run inference directly in the terminal:
./llama-cli -hf meshllm/Qwen3.8-Flash-Next-UD-IQ1_S-layers:BF16

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 meshllm/Qwen3.8-Flash-Next-UD-IQ1_S-layers:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf meshllm/Qwen3.8-Flash-Next-UD-IQ1_S-layers:BF16

Use Docker

docker model run hf.co/meshllm/Qwen3.8-Flash-Next-UD-IQ1_S-layers:BF16

LM Studio
Jan

vLLM

How to use meshllm/Qwen3.8-Flash-Next-UD-IQ1_S-layers with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "meshllm/Qwen3.8-Flash-Next-UD-IQ1_S-layers"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "meshllm/Qwen3.8-Flash-Next-UD-IQ1_S-layers",
		"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/meshllm/Qwen3.8-Flash-Next-UD-IQ1_S-layers:BF16

Ollama
How to use meshllm/Qwen3.8-Flash-Next-UD-IQ1_S-layers with Ollama:
```
ollama run hf.co/meshllm/Qwen3.8-Flash-Next-UD-IQ1_S-layers:BF16
```
Unsloth Desktop

How to use meshllm/Qwen3.8-Flash-Next-UD-IQ1_S-layers with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf meshllm/Qwen3.8-Flash-Next-UD-IQ1_S-layers:BF16

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": "meshllm/Qwen3.8-Flash-Next-UD-IQ1_S-layers:BF16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use meshllm/Qwen3.8-Flash-Next-UD-IQ1_S-layers with Docker Model Runner:
```
docker model run hf.co/meshllm/Qwen3.8-Flash-Next-UD-IQ1_S-layers:BF16
```

Lemonade

How to use meshllm/Qwen3.8-Flash-Next-UD-IQ1_S-layers with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull meshllm/Qwen3.8-Flash-Next-UD-IQ1_S-layers:BF16

Run and chat with the model

lemonade run user.Qwen3.8-Flash-Next-UD-IQ1_S-layers-BF16

List all available models

lemonade list

Hermes Agent

How to use meshllm/Qwen3.8-Flash-Next-UD-IQ1_S-layers with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf meshllm/Qwen3.8-Flash-Next-UD-IQ1_S-layers:BF16

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 meshllm/Qwen3.8-Flash-Next-UD-IQ1_S-layers:BF16

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use meshllm/Qwen3.8-Flash-Next-UD-IQ1_S-layers with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf meshllm/Qwen3.8-Flash-Next-UD-IQ1_S-layers:BF16

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 "meshllm/Qwen3.8-Flash-Next-UD-IQ1_S-layers:BF16" \
  --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-UD-IQ1_S

Distributed GGUF inference package for Mesh LLM

Experimental package: artifact integrity may be validated, but runtime, split-correctness, and multimodal certification are still pending. This package is not discoverable through meshllm/catalog@main until its Hugging Face catalog PR is reviewed and merged.

GGUF layer package for running Qwen3.8-Flash-Next-UD-IQ1_S across a local Mesh LLM cluster.

This package is derived from unsloth/Qwen3.8-Flash-Next-GGUF and keeps the original GGUF distribution split into per-layer artifacts for distributed inference.

Highlights

Run locally	Pool multiple machines	OpenAI-compatible	Package variant
Private inference on your hardware	Split layers across peers	Serve `/v1/chat/completions` locally	`Q1_S` layer package

Model Overview

Property	Value
Source model	unsloth/Qwen3.8-Flash-Next-GGUF
Model id	`unsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ1_S`
Family	Qwen3
Parameter scale	not recorded
Quantization	`Q1_S`
Layer count	48
Activation width	not recorded
Package size	70.1 GB
Source file	`UD-IQ1_S/Qwen3.8-Flash-Next-UD-IQ1_S-00001-of-00003.gguf`
Package repo	meshllm/Qwen3.8-Flash-Next-UD-IQ1_S-layers
License	`other` from unsloth/Qwen3.8-Flash-Next-GGUF

Recommended Use

Local and private inference with Mesh LLM.
Multi-machine serving when the full GGUF is too large for one host.
OpenAI-compatible chat/completions workflows through Mesh LLM's local API.

For upstream architecture details, chat template guidance, sampling recommendations, license terms, and benchmark notes, see the source model card: unsloth/Qwen3.8-Flash-Next-GGUF.

Quickstart

# Run this on each machine that should contribute memory/compute.
mesh-llm serve --model "meshllm/Qwen3.8-Flash-Next-UD-IQ1_S-layers" --split

# Check the mesh and discover the OpenAI-compatible model name.
curl -s http://localhost:3131/api/status
curl -s http://localhost:3131/v1/models

# Send an OpenAI-compatible chat request.
curl -s http://localhost:3131/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "unsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ1_S",
    "messages": [{"role": "user", "content": "Write a tiny hello-world function in Rust."}],
    "max_tokens": 128
  }'

Package Variant

Property	Value
Format	`layer-package`
Canonical source ref	`unsloth/Qwen3.8-Flash-Next-GGUF@38bb39ee97821de2c9009abb7e93950eec396e66/UD-IQ1_S/Qwen3.8-Flash-Next-UD-IQ1_S-00001-of-00003.gguf`
Source revision	`38bb39ee97821de2c9009abb7e93950eec396e66`
Source SHA-256	`88a1420825a9304063e882ada29d438263617f51ac8923d438d927496693bafd`
Skippy ABI	`0.1.48`
Package manifest SHA-256	`0c2ea144eb70d052376ef089d31db50c0a0312bcb37cbf5c1c96e8f544d86a1d`

What Is Included

Artifact	Path	Contents	SHA-256
Manifest	`model-package.json`	Package schema, source identity, checksums	`0c2ea144eb70d052376ef089d31db50c0a0312bcb37cbf5c1c96e8f544d86a1d`
Metadata	`shared/metadata.gguf`	3 tensors, 17.1 MB	`67962a3bfe9b04327f35acab41dd85c0d612b8fe99ea4b5dd8232a3e2fe67ba4`
Embeddings	`shared/embeddings.gguf`	4 tensors, 358.1 MB	`62e72c6fceed1c75a45784d0e3e86b1fc1bb21a6edadd3c35c7f86fd538cd868`
Output head	`shared/output.gguf`	4 tensors, 358.1 MB	`4d902623ba5d79899777b687a894a7ac22eaecd77f28c37eb6555fd2c3943f83`
Transformer layers	`layers/layer-*.gguf`	48 layer artifacts, 1363 tensors, 67.7 GB	`see model-package.json`
Projector	`projectors/mmproj-BF16.gguf`	mmproj projector, 865.5 MB	`2e788f8c511d8093c7b43cb87b2fd7e14228340318057f8fb20c86df2efe2355`
Projector	`projectors/mmproj-F16.gguf`	mmproj projector, 862.1 MB	`1f7b7f0b984cf065c604360c29c8098362ed61b290db0ff12c6f360bb1a8a980`

Validation

Generated by the Mesh LLM HF Jobs splitter from mesh-llm ref main. Each artifact is checksummed as it is written, uploaded to this repository, and removed from the job workspace before the next artifact is produced.

skippy-model-package write-package "/source/UD-IQ1_S/Qwen3.8-Flash-Next-UD-IQ1_S-00001-of-00003.gguf" --out-dir "/tmp/meshllm-layer-job-meshllm_Qwen3.8-Flash-Next-UD-IQ1_S-layers-1/package"

Model tree for meshllm/Qwen3.8-Flash-Next-UD-IQ1_S-layers

Base model

Qwen/Qwen3.8-Flash-Next

Quantized

unsloth/Qwen3.8-Flash-Next-GGUF

Quantized

(2)

this model

meshllm
/

Qwen3.8-Flash-Next-UD-IQ1_S-layers

Qwen3.8-Flash-Next-UD-IQ1_S

Highlights

Model Overview

Recommended Use

Quickstart

Package Variant

What Is Included

Validation

Links

Model tree for meshllm/Qwen3.8-Flash-Next-UD-IQ1_S-layers