EpsteinFilez-8B-GGUF

An 8B parameter GGUF model built on the Qwen3 architecture. Optimized for local inference with Q4_K_M quantization.

Available Quantizations

File	Quant	Size
EpsteinFilez-8B-Q4_K_M.gguf	Q4_K_M	~4.7 GB

Usage

Works with any GGUF-compatible runtime:

# llama.cpp
./llama-cli -m EpsteinFilez-8B-Q4_K_M.gguf -p "Your prompt here"

# Ollama
ollama create epsteinfilez -f Modelfile
ollama run epsteinfilez

# LM Studio — just drag and drop the .gguf file

Details

• Architecture: Qwen3
• Parameters: 8B
• Format: GGUF (Q4_K_M)
• License: Apache 2.0