gemma-4-E4B-it-Q4_K_M
Distributed GGUF inference package for Mesh LLM
GGUF layer package for running gemma-4-E4B-it-Q4_K_M across a local Mesh LLM cluster.
This package is derived from unsloth/gemma-4-E4B-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/gemma-4-E4B-it-GGUF |
| Model id | unsloth/gemma-4-E4B-it-GGUF:Q4_K_M |
| Family | Gemma |
| Parameter scale | 4B |
| Quantization | Q4_K_M |
| Layer count | 42 |
| Activation width | 2560 |
| Package size | 7.5 GB |
| Source file | gemma-4-E4B-it-Q4_K_M.gguf |
| Package repo | meshllm/gemma-4-E4B-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/gemma-4-E4B-it-GGUF.
Quickstart
# Run this on each machine that should contribute memory/compute.
mesh-llm serve --model "meshllm/gemma-4-E4B-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/gemma-4-E4B-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/gemma-4-E4B-it-GGUF@main/gemma-4-E4B-it-Q4_K_M.gguf |
| Source revision | main |
| Source SHA-256 | 519b9793ed6ce0ff530f1b7c96e848e08e49e7af4d57bb97f76215963a54146d |
| Skippy ABI | 0.1.27 |
| Package manifest SHA-256 | 6ede53efea5569551806dc4e08c5f818f3f9a90ebf1023f62435e2b562381a67 |
What Is Included
| Artifact | Path | Contents | SHA-256 |
|---|---|---|---|
| Manifest | model-package.json | Package schema, source identity, checksums | 6ede53efea5569551806dc4e08c5f818f3f9a90ebf1023f62435e2b562381a67 |
| Metadata | shared/metadata.gguf | 3 tensors, 67.6 MB | e953ebb72a50df5e0f6e75d3e32b36a97d4019848f2fadc59f647b0d77be7a17 |
| Embeddings | shared/embeddings.gguf | 5 tensors, 2.2 GB | 8c6eb0117930a11f3d2ff8c3c15a89dafe6bb6b7611e8b9e64d258cd098a5a09 |
| Output head | shared/output.gguf | 4 tensors, 67.6 MB | 2d29952a8f165ba5ac19dd7b22a2e652abb92071024ee7237f338fa58a4adb01 |
| Transformer layers | layers/layer-*.gguf | 42 layer artifacts, 840 tensors, 5.2 GB | see model-package.json |
Validation
Generated by the Mesh LLM HF Jobs splitter from mesh-llm ref 6424e8c8f60728a4303920196cfbb7c088d0e863.
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/gemma-4-E4B-it-Q4_K_M.gguf" --out-dir "/tmp/meshllm-layer-job-meshllm_gemma-4-E4B-it-Q4_K_M-layers-199/package"
Links
- Source model: unsloth/gemma-4-E4B-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