Alduin 4B IT Base - GGUF
Quantized GGUF versions of Muhammadreza/alduin-4b-it-base.
Quantized by saeedalone
Files
| File | Quant | Description |
|---|---|---|
alduin-4b-it-base-Q4_K_M.gguf |
Q4_K_M | Best balance of size and quality |
Usage
llama.cpp
./llama-cli -m alduin-4b-it-base-Q4_K_M.gguf -p "Your prompt"
Ollama
ollama run hf.co/saeedalone/alduin-4b-it-base-GGUF
LM Studio
Search saeedalone/alduin-4b-it-base-GGUF in the model browser.
- Downloads last month
- 465
GGUF
Model size
4B params
Architecture
gemma3
Hardware compatibility
Log In to add your hardware
4-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for saeedalone/alduin-4b-it-base-GGUF
Base model
google/gemma-3-4b-pt Finetuned
google/gemma-3-4b-it Finetuned
Muhammadreza/alduin-4b-it-base