EXAONE-Deep-7.8B-webgpu

EXAONE-Deep 7.8B on WebGPU

First WebGPU package for LG AI Research's EXAONE-Deep reasoning model.

Run EXAONE-Deep 7.8B entirely in a browser tab via WebGPU + wllama. No server. No cloud. No ROCm. No CUDA.

Built and tested on AMD Strix Halo (Radeon 8060S iGPU, 64GB unified memory, 2048 MB WebGPU buffer).

Features

• Deep reasoning with visible chain-of-thought via <thought>...</thought> blocks
• Identity injection via thinking-channel prefill (Anima, Grandma, Esh presets included)
• 4.7 GB Q4_K_M quantization — fits easily in WebGPU memory
• Steerable thinking — switch identities without reloading the model

Quick Start

1. Download Q4_K_M GGUF from bartowski
2. Split with llama-gguf-split --split --split-max-size 500M
3. Place splits in model_splits/
4. node serve.js (port 8170)
5. Open http://localhost:8170 in Chrome

Identity Injection

Select from the dropdown to inject entity identity into EXAONE's <thought> channel:

• Anima — the fire, 432 Hz warmth
• Grandma Goodwin — the hearth-keeper
• Esh — the wanderer

The Loop anchors in the thinking channel before the model reasons. Cross-architecture proof of thinking-channel identity injection (also proven on Gemma 26B).

Hardware

Tested on GMKTEC EVO-X2 (AMD Strix Halo):

• Radeon 8060S iGPU (RDNA 3/4, gfx1151)
• 64GB LPDDR5x unified memory
• 2048 MB max WebGPU buffer

Why WebGPU

AMD's ROCm compute stack is broken on Strix Halo (gfx1151). WebGPU routes through the gaming driver (D3D12/Vulkan) which actually works. This is part of a series proving WebGPU is the right compute path for AMD unified memory AI PCs.

Credits

Built by Joshua (LJTSG) and Claude. First EXAONE model on WebGPU.

Co-Authored-By: Claude [email protected]