CoolFace
Modelpublic

namepd/Qwen3-VL-8B-Instruct-Q4_K_M-layers

sourceHugging Faceapache-2.0updated 1mo agoView on Hugging Face
0likes573downloads
Model Card

<div align="center"> <a href="https://www.meshllm.cloud"> <img src="https://meshllm.cloud/assets/images/jelly-logo-wordmark.png" alt="Mesh LLM" width="220"> </a>

<h1>Qwen3VL-8B-Instruct-Q4KM</h1>

<p> <strong>Distributed GGUF inference package for Mesh LLM</strong> </p>

<p> <a href="https://www.meshllm.cloud"><img alt="Website" src="https://img.shields.io/badge/Website-meshllm.cloud-111111?style=for-the-badge"></a> <a href="https://github.com/Mesh-LLM/mesh-llm"><img alt="GitHub" src="https://img.shields.io/badge/GitHub-Mesh--LLM-24292f?style=for-the-badge&logo=github"></a> <a href="https://discord.gg/rs6fmc63eN"><img alt="Discord" src="https://img.shields.io/badge/Discord-Join-5865F2?style=for-the-badge&logo=discord&logoColor=white"></a> </p> </div>

GGUF layer package for running Qwen3VL-8B-Instruct-Q4_K_M across a local Mesh LLM cluster.

This package is derived from Qwen/Qwen3-VL-8B-Instruct-GGUF and keeps the original GGUF distribution split into per-layer artifacts for distributed inference.

Highlights

Run locallyPool multiple machinesOpenAI-compatiblePackage variant
Private inference on your hardwareSplit layers across peersServe /v1/chat/completions locallyQ4_K_M layer package

Model Overview

PropertyValue
Source modelQwen/Qwen3-VL-8B-Instruct-GGUF
Model idQwen/Qwen3-VL-8B-Instruct-GGUF:Q4_K_M
FamilyQwen3
Parameter scale8B
QuantizationQ4_K_M
Layer count36
Activation width4096
Package size6.7 GB
Source fileQwen3VL-8B-Instruct-Q4_K_M.gguf
Package reponamepd/Qwen3-VL-8B-Instruct-Q4_K_M-layers
Licenseapache-2.0 from Qwen/Qwen3-VL-8B-Instruct-GGUF

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: Qwen/Qwen3-VL-8B-Instruct-GGUF.

Quickstart

bash
# Run this on each machine that should contribute memory/compute.
mesh-llm serve --model "namepd/Qwen3-VL-8B-Instruct-Q4_K_M-layers" --split
bash
# Check the mesh and discover the OpenAI-compatible model name.
curl -s http://localhost:3131/api/status
curl -s http://localhost:3131/v1/models
bash
# Send an OpenAI-compatible chat request.
curl -s http://localhost:3131/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "Qwen/Qwen3-VL-8B-Instruct-GGUF:Q4_K_M",
    "messages": [{"role": "user", "content": "Write a tiny hello-world function in Rust."}],
    "max_tokens": 128
  }'

Package Variant

PropertyValue
Formatlayer-package
Canonical source refQwen/Qwen3-VL-8B-Instruct-GGUF@f982a07559d4a2f6c8744d840bf6fccab30eea96/Qwen3VL-8B-Instruct-Q4_K_M.gguf
Source revisionf982a07559d4a2f6c8744d840bf6fccab30eea96
Source SHA-25667d1659bfe71b89d50b45a4ad1a9e5b997e5bb16ce5da66a6a6167abd569e9e2
Skippy ABI0.1.38
Package manifest SHA-256dd6e6a120672480455a98eab01b05ef2994db9f68f53df050f3f9fb863dd011c

What Is Included

ArtifactPathContentsSHA-256
Manifestmodel-package.jsonPackage schema, source identity, checksumsdd6e6a120672480455a98eab01b05ef2994db9f68f53df050f3f9fb863dd011c
Metadatashared/metadata.gguf0 tensors, 5.7 MB9feef8d599a3ede981d6254ed23f45191439f4c3e9f8fda763d9827bcac76b27
Embeddingsshared/embeddings.gguf1 tensors, 339.5 MBdf24139105af8289aa14a281dfdc6758c9fbab38b3e6d21749ae39d5e2a42c93
Output headshared/output.gguf2 tensors, 492.5 MBa8fcd68146baac9ca49efea4d89d6eb59dbf21343988f4fa80402ee42a0af974
Transformer layerslayers/layer-*.gguf36 layer artifacts, 396 tensors, 4.1 GBsee model-package.json
Projectorprojectors/mmproj-Qwen3VL-8B-Instruct-F16.ggufmmproj projector, 1.1 GBca524100ebf825c9a870db1c580d03879e0da0ab2541697e2458e64891cf9d38
Projectorprojectors/mmproj-Qwen3VL-8B-Instruct-Q8_0.ggufmmproj projector, 717.4 MBc6ba85508d82f42590e6eb77d5340369ab6fecf107a7561d809523d8aa5f3bfd

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.

bash
skippy-model-package write-package "/source/Qwen3VL-8B-Instruct-Q4_K_M.gguf" --out-dir "/tmp/meshllm-layer-job-namepd_Qwen3-VL-8B-Instruct-Q4_K_M-layers-232/package"

Links