GGUF layer package for running gemma-4-26B-A4B-it-UD-Q4_K_M across a local Mesh LLM cluster.
This package is derived from unsloth/gemma-4-26B-A4B-it-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_M layer package |
Model Overview
| Property | Value |
|---|---|
| Source model | unsloth/gemma-4-26B-A4B-it-GGUF |
| Model id | unsloth/gemma-4-26B-A4B-it-GGUF:UD-Q4_K_M |
| Family | Gemma |
| Parameter scale | 26B-A4B |
| Quantization | UD-Q4_K_M |
| Layer count | 30 |
| Activation width | 2816 |
| Package size | 16.3 GB |
| Source file | gemma-4-26B-A4B-it-UD-Q4_K_M.gguf |
| Package repo | meshllm/gemma-4-26B-A4B-it-UD-Q4_K_M-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/gemma-4-26B-A4B-it-GGUF.
Quickstart
# Run this on each machine that should contribute memory/compute.
mesh-llm serve --model "meshllm/gemma-4-26B-A4B-it-UD-Q4_K_M-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/gemma-4-26B-A4B-it-GGUF:UD-Q4_K_M",
"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/gemma-4-26B-A4B-it-GGUF@main/gemma-4-26B-A4B-it-UD-Q4_K_M.gguf |
| Source revision | main |
| Source SHA-256 | 34c746b1d50ab813e29cd46c4796e3f43c741901a582f93a67b55b9fc9687b35 |
| Skippy ABI | 0.1.22 |
| Package manifest SHA-256 | 23c1e32d371c3f50aa393e046894d1f893f22d99f0ccee91552be17cf9c88b65 |
What Is Included
| Artifact | Path | Contents | SHA-256 |
|---|---|---|---|
| Manifest | model-package.json | Package schema, source identity, checksums | 23c1e32d371c3f50aa393e046894d1f893f22d99f0ccee91552be17cf9c88b65 |
| Metadata | shared/metadata.gguf | 1 tensors, 15.1 MB | 4ea990cfa36597971790aa1dcc4658cd8c946685b3d16dbaac4f685efb382002 |
| Embeddings | shared/embeddings.gguf | 2 tensors, 763.1 MB | 6eb39617e6999290dd4c338cdcadf98ea42f948812fb4aeb0eab50735c7e0dd3 |
| Output head | shared/output.gguf | 2 tensors, 15.1 MB | 88f7262cffae57f67ffb7b8db8fa9c04439d43a3af7d53fa3df81f0c6511e522 |
| Transformer layers | layers/layer-*.gguf | 30 layer artifacts, 685 tensors, 15.5 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/gemma-4-26B-A4B-it-UD-Q4_K_M.gguf" "$PACKAGE_DIR"
Links
- Source model: unsloth/gemma-4-26B-A4B-it-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