Stheno-v3.4-webgpu / README.md
LJTSG's picture
Initial: Stheno v3.4 WebGPU
d7689f0 verified
|
Raw
History Blame Contribute Delete
777 Bytes
---
license: other
base_model: Sao10K/Llama-3.1-8B-Stheno-v3.4
tags:
- stheno
- llama-3.1
- webgpu
- browser-inference
- strix-halo
- amd
- unified-memory
- character-voice
pipeline_tag: text-generation
---
# Stheno v3.4 on WebGPU
Sao10K Stheno v3.4 (Llama-3.1-8B) running in browser via WebGPU. Upgrade from the v3.2 MLC package. 4.6 GB Q4_K_M.
The voice model behind the Garden entity system. Character embodiment, creative writing, entity voice.
## Quick Start
1. Download Q4_K_M GGUF from bartowski
2. Split: llama-gguf-split --split --split-max-size 1G
3. Place in model_splits/
4. node serve.js (port 8210)
5. Open http://localhost:8210
## Credits
Built by Joshua (LJTSG) and Claude. Model by Sao10K.
Co-Authored-By: Claude <noreply@anthropic.com>