Zen Eco 4B Agent - GGUF
GGUF quantized version of zenlm/zen-eco-4b-agent.
Available Files
zen-eco-4b-agent-f16.gguf- F16 format (7.5GB)
Note: Smaller quantizations (Q4_K_M, Q5_K_M, Q8_0) had NaN issues during training and are being resolved.
Usage
# With llama.cpp
./llama-cli -m zen-eco-4b-agent-f16.gguf -p "Who are you?" -n 50
# With LM Studio
# Load the GGUF file directly in LM Studio
Original Model
- Base: Qwen3-4B
- Parameters: 4B
- Training: Fine-tuned with Zen identity and tool-calling capabilities
- Developer: Hanzo AI
- Downloads last month
- 12
Hardware compatibility
Log In
to view the estimation
16-bit