GGUF layer package for running Llama-4-Scout-17B-16E-Instruct-UD-Q4_K_XL across a local Mesh LLM cluster.
This package is derived from unsloth/Llama-4-Scout-17B-16E-Instruct-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 | UD-Q4_K_XL layer package |
Model Overview
| Property | Value |
|---|---|
| Source model | unsloth/Llama-4-Scout-17B-16E-Instruct-GGUF |
| Model id | unsloth/Llama-4-Scout-17B-16E-Instruct-GGUF:UD-Q4_K_XL |
| Family | Llama |
| Parameter scale | 17B |
| Quantization | UD-Q4_K_XL |
| Layer count | 48 |
| Activation width | 5120 |
| Package size | 58.3 GB |
| Source file | UD-Q4_K_XL/Llama-4-Scout-17B-16E-Instruct-UD-Q4_K_XL-00001-of-00002.gguf |
| Package repo | meshllm/Llama-4-Scout-17B-16E-Instruct-UD-Q4_K_XL-layers |
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/Llama-4-Scout-17B-16E-Instruct-GGUF.
Quickstart
# Run this on each machine that should contribute memory/compute.
mesh-llm serve --model "meshllm/Llama-4-Scout-17B-16E-Instruct-UD-Q4_K_XL-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/Llama-4-Scout-17B-16E-Instruct-GGUF:UD-Q4_K_XL",
"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/Llama-4-Scout-17B-16E-Instruct-GGUF@main/UD-Q4_K_XL/Llama-4-Scout-17B-16E-Instruct-UD-Q4_K_XL-00001-of-00002.gguf |
| Source revision | main |
| Source SHA-256 | bc2e19afa97799f31a9e99818f235bb3a16fa12b695cf49d3ab7c93eca1d4d45 |
| Skippy ABI | 0.1.24 |
| Package manifest SHA-256 | b26056cb7558565a16ce21ea4155a9d893779340ca2bcd9be2c9342f34b5dc4e |
What Is Included
| Artifact | Path | Contents | SHA-256 |
|---|---|---|---|
| Manifest | model-package.json | Package schema, source identity, checksums | b26056cb7558565a16ce21ea4155a9d893779340ca2bcd9be2c9342f34b5dc4e |
| Metadata | shared/metadata.gguf | 1 tensors, 12.5 MB | ac53081e0403a186f0b763a3997c65fb5b851aa1f4f300808a61f4c8ab63d56c |
| Embeddings | shared/embeddings.gguf | 2 tensors, 567.4 MB | 8b97e7c7373b64dc41db22d34b1db1f750b90e55ac78b09af3f72d64938c8851 |
| Output head | shared/output.gguf | 3 tensors, 821.8 MB | f3e37c93e4cfacfb719eb0af4c73aa9823dda79a9bd1cc05520a3af717cf807c |
| Transformer layers | layers/layer-*.gguf | 48 layer artifacts, 672 tensors, 57.0 GB | see model-package.json |
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-Q4_K_XL/Llama-4-Scout-17B-16E-Instruct-UD-Q4_K_XL-00001-of-00002.gguf" --out-dir "/tmp/meshllm-layer-job-meshllm_Llama-4-Scout-17B-16E-Instruct-UD-Q4_K_XL-layers-200/package"
Links
- Source model: unsloth/Llama-4-Scout-17B-16E-Instruct-GGUF
- Mesh LLM website: meshllm.cloud
- Mesh LLM: github.com/Mesh-LLM/mesh-llm
- Discord: discord.gg/rs6fmc63eN
- Package catalog: meshllm/catalog
- Package format: layer-package-repos.md