GGUF layer package for running diffusiongemma-26B-A4B-it-Q4_K_M across a local Mesh LLM cluster.
This package is derived from unsloth/diffusiongemma-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 | Q4_K_M layer package |
Model Overview
| Property | Value |
|---|---|
| Source model | unsloth/diffusiongemma-26B-A4B-it-GGUF |
| Model id | unsloth/diffusiongemma-26B-A4B-it-GGUF:Q4_K_M |
| Family | Gemma |
| Parameter scale | 26B-A4B |
| Quantization | Q4_K_M |
| Layer count | 30 |
| Activation width | 2816 |
| Package size | 16.4 GB |
| Source file | diffusiongemma-26B-A4B-it-Q4_K_M.gguf |
| Package repo | meshllm/diffusiongemma-26B-A4B-it-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/diffusiongemma-26B-A4B-it-GGUF.
Quickstart
# Run this on each machine that should contribute memory/compute.
mesh-llm serve --model "meshllm/diffusiongemma-26B-A4B-it-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/diffusiongemma-26B-A4B-it-GGUF: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/diffusiongemma-26B-A4B-it-GGUF@main/diffusiongemma-26B-A4B-it-Q4_K_M.gguf |
| Source revision | main |
| Source SHA-256 | d2ca2c032ebfb23cf2d1794a3465e615c7545634d46b3c30652a26d8b07c4ad3 |
| Skippy ABI | 0.1.25 |
| Package manifest SHA-256 | 39f27bda195fc2278ec4e3f558576c3902def47e500d63734d3b530417b55cc2 |
What Is Included
| Artifact | Path | Contents | SHA-256 |
|---|---|---|---|
| Manifest | model-package.json | Package schema, source identity, checksums | 39f27bda195fc2278ec4e3f558576c3902def47e500d63734d3b530417b55cc2 |
| Metadata | shared/metadata.gguf | 5 tensors, 25.3 MB | 458d44ddd2f111fd4dd7fd6b7d6aa4f8831c999f715a60b1fe4a0194e80ad256 |
| Embeddings | shared/embeddings.gguf | 6 tensors, 602.8 MB | a543ceb86296e24c7dab5b03791f7dd6546ddf969bf922bb8c9728dd1ab0aba1 |
| Output head | shared/output.gguf | 6 tensors, 25.4 MB | f50a9e5f42769bf62644683d34b8386b84f8f63f73aac1bb2cdfb6fbf0859d3f |
| Transformer layers | layers/layer-*.gguf | 30 layer artifacts, 835 tensors, 15.8 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/diffusiongemma-26B-A4B-it-Q4_K_M.gguf" --out-dir "/tmp/meshllm-layer-job-meshllm_diffusiongemma-26B-A4B-it-Q4_K_M-layers-199/package"
Links
- Source model: unsloth/diffusiongemma-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