Model Intelligence Sheet
Kype720184/DorsetHeatwaveLLM_GGUF overview
Note: THIS IS THE EXPERIMENTAL GGUF VERSION OF DorsetHeatwaveLLM IT MAY BREAK OR HALUCINATE OR MAY NOT WORK AND IS NOT SIMPLE EXPECT POTENTIAL DISSATISFACTION …
Runs locally from ~1.03 GB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
Model Details
| Model ID | Kype720184/DorsetHeatwaveLLM_GGUF |
|---|---|
| Author | Kype720184 |
| Pipeline | — |
| License | agpl-3.0 |
| Base model | unsloth/Qwen3-1.7B-Base |
| Last modified | 2026-06-27T12:27:40.000Z |
Model README
---
tags:
- gguf
- llama.cpp
- unsloth
license: agpl-3.0
language:
- en
base_model:
- unsloth/Qwen3-1.7B-Base
datasets:
- common-pile/uk_hansard
---
Note: THIS IS THE EXPERIMENTAL GGUF VERSION OF DorsetHeatwaveLLM! IT MAY BREAK OR HALUCINATE OR MAY NOT WORK AND IS NOT SIMPLE! EXPECT POTENTIAL DISSATISFACTION!
For the original non-GGUF version and the README, CLICK ME!
The URL is https://huggingface.co/Kype720184/DorsetHeatwaveLLM.
Building notes
- Please download the Q4_K_M and Q8_0 files manually with the obviously corresponding README
- To build the Q4 version: ollama create DorsetHeatwaveLLM-q4 -f ./Modelfile.q4_k_m
- To build the Q8 version: ollama create DorsetHeatwaveLLM-q8 -f ./Modelfile.q8_0
Run Kype720184/DorsetHeatwaveLLM_GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models