GGUF layer package for running Qwen3-Coder-480B-A35B-Instruct-UD-Q4_K_XL across a local Mesh LLM cluster.
This package is derived from unsloth/Qwen3-Coder-480B-A35B-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/Qwen3-Coder-480B-A35B-Instruct-GGUF |
| Model id | unsloth/Qwen3-Coder-480B-A35B-Instruct-GGUF:UD-Q4_K_XL |
| Family | Qwen3 |
| Parameter scale | 480B-A35B |
| Quantization | UD-Q4_K_XL |
| Layer count | 62 |
| Activation width | 6144 |
| Package size | 257.0 GB |
| Source file | UD-Q4_K_XL/Qwen3-Coder-480B-A35B-Instruct-UD-Q4_K_XL-00001-of-00006.gguf |
| Package repo | meshllm/Qwen3-Coder-480B-A35B-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/Qwen3-Coder-480B-A35B-Instruct-GGUF.
Quickstart
# Run this on each machine that should contribute memory/compute.
mesh-llm serve --model "meshllm/Qwen3-Coder-480B-A35B-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/Qwen3-Coder-480B-A35B-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/Qwen3-Coder-480B-A35B-Instruct-GGUF@main/UD-Q4_K_XL/Qwen3-Coder-480B-A35B-Instruct-UD-Q4_K_XL-00001-of-00006.gguf |
| Source revision | main |
| Source SHA-256 | ae0d41c4baa6871a3702e389be00dac564fd28ad407504ec8e2f46b7c4ee0a47 |
| Skippy ABI | 0.1.14 |
| Package manifest SHA-256 | f34673d0db728c489cc99ec81b730045ff0b7954b5d04af17d8528898f337402 |
What Is Included
| Artifact | Path | Contents | SHA-256 |
|---|---|---|---|
| Manifest | model-package.json | Package schema, source identity, checksums | f34673d0db728c489cc99ec81b730045ff0b7954b5d04af17d8528898f337402 |
| Metadata | shared/metadata.gguf | 0 tensors, 5.7 MB | e563297f5c4c1015779071aed73292c7452efd382fdff3b44a19f7c731058745 |
| Embeddings | shared/embeddings.gguf | 1 tensors, 506.4 MB | a263cf9d3cab00b3ac9e0f62294b0c1c7e0cb614d0e7054aadaa6329b6141d92 |
| Output head | shared/output.gguf | 2 tensors, 736.0 MB | 91b0cfb3bd12021bdba24efa5a3c3702374d4fccef1e9caf3753874cc3c9311b |
| Transformer layers | layers/layer-*.gguf | 62 layer artifacts, 744 tensors, 255.8 GB | see model-package.json |
Validation
Generated by the Mesh LLM HF Jobs splitter from mesh-llm ref main and validated before upload:
skippy-model-package validate-package "/source/UD-Q4_K_XL/Qwen3-Coder-480B-A35B-Instruct-UD-Q4_K_XL-00001-of-00006.gguf" "$PACKAGE_DIR"
Links
- Source model: unsloth/Qwen3-Coder-480B-A35B-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