Downloads · 30 days
23
11% of all-time downloads
Tejapriyan-8B-GGUF
teja161615/Tejapriyan-8B-GGUF
Tejapriyan-8B-GGUF is a text generation model from teja161615. Use it when you need the model to write or continue text. The card lists the license as apache-2.0.
Quantized GGUF weights of Tejapriyan-8B for ultra-fast local inference on CPU and GPU with Ollama, llama.cpp, and LM Studio. Fine-tuned and quantized by Teja Priyan.
All-time downloads
211
Public
Repo size
4.7 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf4.7 GB · 100%
At a glance
- Task
- Text Generation
- License
- apache-2.0
- Access
- Public
- Created
- Sep 1, 2026
- Updated
- Sep 5, 2026
- SHA
- 3f4b0ca4
Try a prompt
Base models
Model card
From the Hugging Face model README
Tejapriyan-8B-GGUF ⚡
Quantized GGUF weights of Tejapriyan-8B for ultra-fast local inference on CPU and GPU with Ollama, llama.cpp, and LM Studio.
Fine-tuned and quantized by Teja Priyan.
- Base Safetensors Repository: teja161615/Tejapriyan-8B
- Live Interactive Web Playground: tejapriyan.vercel.app
📦 Available Files & Quantizations
| File Name | Quantization | Size | RAM / VRAM Required | Recommended For |
|---|---|---|---|---|
tejapriyan-q4_k_m.gguf | Q4_K_M (Medium) | ~4.7 GB | ~5.5 GB | Best balance of speed, size & quality (Recommended) |
tejapriyan-q8_0.gguf | Q8_0 (8-bit) | ~8.5 GB | ~9.2 GB | Near-lossless accuracy on high-spec systems |
tejapriyan-f16.gguf | F16 (Full Precision) | ~15.2 GB | ~16.5 GB | Full baseline fidelity |
🚀 Quickstart: Run with Ollama
Option A: One-Command Download & Run
# Download the GGUF file directly
curl -L -o tejapriyan-q4_k_m.gguf https://huggingface.co/teja161615/Tejapriyan-8B-GGUF/resolve/main/tejapriyan-q4_k_m.gguf
- Task
- Text Generation
- License
- apache-2.0
- Languages
- en
- Created
- Sep 1, 2026
- Updated
- Sep 5, 2026