GGUF layer package for running Ornith-1.0-35B-UD-Q4_K_XL across a local Mesh LLM cluster.
This package is derived from unsloth/Ornith-1.0-35B-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/Ornith-1.0-35B-GGUF |
| Model id | unsloth/Ornith-1.0-35B-GGUF:UD-Q4_K_XL |
| Family | Ornith |
| Parameter scale | 35B |
| Quantization | UD-Q4_K_XL |
| Layer count | 40 |
| Activation width | 2048 |
| Package size | 21.2 GB |
| Source file | Ornith-1.0-35B-UD-Q4_K_XL.gguf |
| Package repo | meshllm/Ornith-1.0-35B-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/Ornith-1.0-35B-GGUF.
Quickstart
# Run this on each machine that should contribute memory/compute.
mesh-llm serve --model "meshllm/Ornith-1.0-35B-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/Ornith-1.0-35B-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/Ornith-1.0-35B-GGUF@main/Ornith-1.0-35B-UD-Q4_K_XL.gguf |
| Source revision | main |
| Source SHA-256 | 21be012dc5c193ea237b3e7fccc3099674da40552ae0a0e2a1086c30cb2c2929 |
| Skippy ABI | 0.1.30 |
| Package manifest SHA-256 | 6d46be1c6117b403d3ec02150229f4bfe721ac03af118cdb46794679f752583b |
What Is Included
| Artifact | Path | Contents | SHA-256 |
|---|---|---|---|
| Manifest | model-package.json | Package schema, source identity, checksums | 6d46be1c6117b403d3ec02150229f4bfe721ac03af118cdb46794679f752583b |
| Metadata | shared/metadata.gguf | 0 tensors, 10.4 MB | ff3a2c2451e0ae956f7a559252ff82e80f49d451fde7d59e705b6762199b6810 |
| Embeddings | shared/embeddings.gguf | 1 tensors, 525.7 MB | 057819e30ec781d70a7582c666e0b1153759e169858ab8d4a7e283ad2d671c3c |
| Output head | shared/output.gguf | 2 tensors, 525.8 MB | f9eb60cab76d7d318076a69df0515463066a5185eddfde1cccd42fb40e720ea5 |
| Transformer layers | layers/layer-*.gguf | 40 layer artifacts, 730 tensors, 20.2 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/Ornith-1.0-35B-UD-Q4_K_XL.gguf" --out-dir "/tmp/meshllm-layer-job-meshllm_Ornith-1.0-35B-UD-Q4_K_XL-layers-199/package"
Links
- Source model: unsloth/Ornith-1.0-35B-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