Model Intelligence Sheet
elliotthwang/TW-Llama-3.1-8B-GGUF overview
TW Llama 3.1 8B GGUF : GGUF 繁體台灣中文 微調loss: 0.2257 This model was finetuned and converted to GGUF format using Unsloth https://github.com/unslothai/unsloth . Ex…
Runs locally from ~4.58 GB disk (8 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
1 GGUF files detected
Direct downloads for local inference
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| Meta-Llama-3.1-8B-Instruct.Q4_K_M.gguf | GGUF | GGUF | 4.58 GB | Download |
Model Details
| Model ID | elliotthwang/TW-Llama-3.1-8B-GGUF |
|---|---|
| Author | elliotthwang |
| Pipeline | — |
| License | — |
| Base model | — |
| Last modified | 2026-07-29T09:49:14.000Z |
Model README
---
tags:
- gguf
- llama.cpp
- unsloth
---
TW-Llama-3.1-8B-GGUF : GGUF
繁體台灣中文 微調loss: 0.2257
This model was finetuned and converted to GGUF format using Unsloth.
Example usage:
- For text only LLMs:
llama-cli -hf elliotthwang/TW-Llama-3.1-8B-GGUF --jinja - For multimodal models:
llama-mtmd-cli -hf elliotthwang/TW-Llama-3.1-8B-GGUF --jinja
Available Model files:
Meta-Llama-3.1-8B-Instruct.Q4_K_M.gguf
Ollama
An Ollama Modelfile is included for easy deployment.
This was trained 2x faster with Unsloth
Run elliotthwang/TW-Llama-3.1-8B-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models