Downloads · 30 days
161
5% of all-time downloads
graig-code-turbo-fast-slow-4.5-mini
electron271/graig-code-turbo-fast-slow-4.5-mini
graig-code-turbo-fast-slow-4.5-mini is a text generation model from electron271. Use it when you need the model to write or continue text. The card lists the license as apache-2.0.
the latest state of the art model in the field of accuracy
All-time downloads
3.4K
Public
Parameters
596M
7 GB on disk
Likes
3
Public
Repo makeup
Click a slice to open those files.
.gguf5.8 GB · 83%
At a glance
- Task
- Text Generation
- License
- apache-2.0
- Model type
- qwen3
- Access
- Public
- Created
- Oct 24, 2025
- Updated
- Oct 24, 2025
- SHA
- f8a94b95
Try a prompt
Base models
Datasets
Model card
From the Hugging Face model README
DISCLAIMER: DO NOT USE THIS IN PUBLIC DEPLOYMENTS WE ARE NOT RESPONSIBLE FOR WHAT THIS MODEL IN PARTICULAR SAYS
THIS IS AN EXPERIMENT
graig-code-turbo-fast-slow-4.5-mini
the latest state of the art model in the field of accuracy
other companies may be trying to reach artificial general intelligence, but we are trying to reach artificial grain intelligence. with the help of our team of the best grain farmers in the world, we are making huge strides in the field. fine tuned fully locally using a RX 9070 XT using unsloth.
ollama run hf.co/electron271/graig-code-turbo-fast-slow-4.5-mini:F16
Recommended Settings
temperature = 0.6top_k = 20min_p = 0.00(llama.cpp's default is 0.1)top_p = 0.95presence_penalty = 0.0 to 2.0(llama.cpp default turns it off, but to reduce repetitions, you can use this) Try 1.0 for example.- Supports up to
131,072context natively but you can set it to32,768tokens for less RAM use
you can also use /no_think for extra chaoticness
- Task
- Text Generation
- Type
- qwen3
- License
- apache-2.0
- Languages
- en
- Created
- Oct 24, 2025
- Updated
- Oct 24, 2025