Downloads · 30 days
20
18% of all-time downloads
Fattah-2.5B-preview-Q8_0-GGUF
Mano200600/Fattah-2.5B-preview-Q8_0-GGUF
Fattah-2.5B-preview-Q8_0-GGUF is a machine learning model from Mano200600. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
This model was converted to GGUF format from belal212/Fattah-2.5B-preview using llama.cpp.
All-time downloads
110
Public
Repo size
2.8 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf2.8 GB · 100%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Apr 8, 2026
- Updated
- Apr 8, 2026
- SHA
- 85432947
Model card
From the Hugging Face model README
Mano200600/Fattah-2.5B-preview-Q8_0-GGUF
This model was converted to GGUF format from belal212/Fattah-2.5B-preview using llama.cpp.
Quantization: Q8_0 — Maximum practical quality (~98%+ of original FP16)
Key Features:
- 8-bit quantization for near-lossless quality
- Optimized for use with llama.cpp
- Compatible with llama-server for efficient serving
- Ideal for small models where storage is not a concern
Refer to the original model card for more details on the base model.
Usage with llama.cpp
1. Install llama.cpp:
brew install llama.cpp # For macOS/Linux
2. Run Inference:
CLI:
llama-cli --hf-repo Mano200600/Fattah-2.5B-preview-Q8_0-GGUF --hf-file fattah-2.5b-preview-q8_0.gguf -p "Your prompt here"
Server:
llama-server --hf-repo Mano200600/Fattah-2.5B-preview-Q8_0-GGUF --hf-file fattah-2.5b-preview-q8_0.gguf -c 2048
For more advanced usage, refer to the llama.cpp repository.
- License
- apache-2.0
- Created
- Apr 8, 2026
- Updated
- Apr 8, 2026