deepreinforce-ai_Ornith-1.0-9B-GGUF

Overview

Llamacpp imatrix Quantizations of Ornith-1.0-9B by deepreinforce-ai

Using llama.cpp release b9781 for quantization.

Original model: https://huggingface.co/deepreinforce-ai/Ornith-1.0-9B

Strengths

• HumanEval+: 86.0% (141/164)
• MBPP+: 87.8% (332/378)
• BFCL (tool calling): 74.8% (400 problems)

Tested Hardware

Benchmarked by Infersec on:

• NVIDIA RTX 5090 (64 GB RAM, 32 GB VRAM, linux)