GGUF layer package for running Qwen3.5-397B-A17B-UD-Q4_K_XL across a local Mesh LLM cluster.
This package is derived from unsloth/Qwen3.5-397B-A17B-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/Qwen3.5-397B-A17B-GGUF |
| Model id | unsloth/Qwen3.5-397B-A17B-GGUF:UD-Q4_K_XL |
| Family | Qwen3 |
| Parameter scale | 397B-A17B |
| Quantization | UD-Q4_K_XL |
| Layer count | 60 |
| Activation width | 4096 |
| Package size | 229.1 GB |
| Source file | UD-Q4_K_XL/Qwen3.5-397B-A17B-UD-Q4_K_XL-00001-of-00006.gguf |
| Package repo | meshllm/Qwen3.5-397B-A17B-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/Qwen3.5-397B-A17B-GGUF.
Quickstart
# Run this on each machine that should contribute memory/compute.
mesh-llm serve --model "meshllm/Qwen3.5-397B-A17B-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/Qwen3.5-397B-A17B-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/Qwen3.5-397B-A17B-GGUF@main/UD-Q4_K_XL/Qwen3.5-397B-A17B-UD-Q4_K_XL-00001-of-00006.gguf |
| Source revision | main |
| Source SHA-256 | 63c290c9be83e1b4dd41833d81bd933afd535d65657579b9f92f5c3f76e0218d |
| Skippy ABI | 0.1.22 |
| Package manifest SHA-256 | 2d191c9f8910241875a70b49baaa1752ce8e4a7a5e9375d4a7a52bcb3f8af67d |
What Is Included
| Artifact | Path | Contents | SHA-256 |
|---|---|---|---|
| Manifest | model-package.json | Package schema, source identity, checksums | 2d191c9f8910241875a70b49baaa1752ce8e4a7a5e9375d4a7a52bcb3f8af67d |
| Metadata | shared/metadata.gguf | 0 tensors, 10.4 MB | 5cc2c548da196afec73b88ae394cdbd348ea0cdfc4b386ff1f4f4391ec31a762 |
| Embeddings | shared/embeddings.gguf | 1 tensors, 1.0 GB | 15e3731580e97a638a9bfd7a0b134f6bfca226e7048c6acbd27445419fad540f |
| Output head | shared/output.gguf | 2 tensors, 1.0 GB | 92e11ed68e619b1864928c93e0e415674a17958f12adec6423dc98b3cd533508 |
| Transformer layers | layers/layer-*.gguf | 60 layer artifacts, 1095 tensors, 227.0 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/Qwen3.5-397B-A17B-UD-Q4_K_XL-00001-of-00006.gguf" --out-dir "/tmp/meshllm-layer-job-meshllm_Qwen3.5-397B-A17B-UD-Q4_K_XL-layers-192/package"
Links
- Source model: unsloth/Qwen3.5-397B-A17B-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