nzgnzg73/llama_cpp_WebUI

nzgnzg73

llamacppWebUI

Github https://github.com/nzgnzg73/llamacppWebUI

Want to talk or ask something?

Just click the YouTube link below! You'll find my 📧 email there and can message me easily. 👇

🎥 YouTube Channel: @nzg73 🔗 https://youtube.com/@NZG73

Contact Email 👇👇👀

E-mail:- nzgnzg73@gmail.com

llama Cpp (cp\gpu) Old Version llama cpp 👇👇👇👇 llama-b7200-bin-win-cpu-x64.zip

NEW Update Version llama cpp 👇👇👇👇

llama-b7541-bin-win-cpu-x64

llama-b7243-bin-win-cuda-12.4-x64

Llama Model Switcher

CMD model_switcher.py

pip install flask

pip install flask psutil GPUtil

Image-Text-to-Text Models

Gemma-3

CPU. RAM 20GB OR GPU. 4 VRAM

1. 1.gemma-3-12b-it-Q4KS.gguf
2. 2.mmproj-model-f16-12B.gguf

-Text-to-Text Models

GPT OSS 20

Qwen3

CPU. RAM 25GB OR GPU. 4 VRAM

1. 1.Qwen3-VL-2B-Instruct-Q8_0.gguf
2. 2.mmproj-Qwen3-VL-2B-Instruct-Q8_0.gguf

Qwen2.5-Omni

CPU. RAM 40GB OR GPU. 8 VRAM

1. 1.Qwen2.5-Omni-7B-BF16.gguf
2. 2.mmproj-F16.gguf 2GB

Audio-Text-to-Text

Llama-3.2

CPU. RAM 10GB

1. 1.Llama-3.2-1B-Instruct-Q4KM.gguf
2. 2.Llama-3.2-1B-Instruct-Q8_0.gguf
3. 3.mmproj-ultravox-v05-llama-32-1b-f16.gguf

run.bat

Local Server

llama-server.exe --n-gpu-layers 2 --ctx-size 111192 -m ".\models\mistralai\mistralaiVoxtral-Mini-3B-2507-Q80.gguf" --mmproj ".\models\mistralai\mmproj-mistralai_Voxtral-Mini-3B-2507-bf16.gguf" --host 0.0.0.0 --port 8005

public URL

llama-server --n-gpu-layers 15 --ctx-size 8192 -m models/ollma/Llama-3.2-1B-Instruct-Q80.gguf --mmproj models/ollma/mmproj-ultravox-v05-llama-3_2-1b-f16.gguf --host 127.0.0.1 --port 8083