LLM EXPLORER 60,645 MODELS INDEXED

NexusRaven 13B GGUF by TheBloke

By TheBloke · 355 downloads
HF Repo ↗ Copy URL

NexusRaven 13B GGUF is an open-source language model by TheBloke. Features: 13b LLM, VRAM: 5.4GB, License: llama2, Quantized, LLM Explorer Score: 0.09.

  Arxiv:2308.12950 Base model:nexusflow/nexusrave... Base model:quantized:nexusflow...   Gguf   Llama   Quantized   Region:us
Model Card on HF 🤗: https://huggingface.co/TheBloke/NexusRaven-13B-GGUF 

NexusRaven 13B GGUF Parameters and Internals

Model Type 
llama
Use Cases 
Areas:
Commercial applications, Research
Applications:
Cybersecurity tools
Primary Use Cases:
Function calling in cybersecurity tools, Generalization to unseen tools
Limitations:
Needs a stop criteria for reflections, Best performance with retrievers in a multi-function environment, Can generate incorrect calls
Considerations:
Use stop criteria for reflections. Ensure proper guardrails for errant behavior.
Additional Notes 
The model benefits from an accompanying retriever to optimize function handling, especially with a saturated context window.
Training Details 
Data Sources:
open-source cybersecurity tools data
Hardware Used:
multi-GPU setup with 8 devices
Model Architecture:
specialized for function calling
Input Output 
Input Format:
Prompt template: '{prompt} '
Accepted Modalities:
Python functions
Performance Tips:
Stop generation at criteria: [\nReflection:] to reduce unnecessary token use.
LLM NameNexusRaven 13B GGUF
Repository 🤗https://huggingface.co/TheBloke/NexusRaven-13B-GGUF 
Model NameNexusraven 13B
Model CreatorNexusflow
Base Model(s)  NexusRaven 13B   Nexusflow/NexusRaven-13B
Model Size13b
Required VRAM5.4 GB
Updated2026-05-24
MaintainerTheBloke
Model Typellama
Model Files  5.4 GB   6.9 GB   6.3 GB   5.7 GB   7.4 GB   7.9 GB   7.4 GB   9.0 GB   9.2 GB   9.0 GB   10.7 GB   13.8 GB
GGUF QuantizationYes
Quantization Typegguf
Model ArchitectureAutoModel
Licensellama2

Best Alternatives to NexusRaven 13B GGUF

Best Alternatives
Context / RAM
Downloads
Likes
MythoMax L2 13B GGUF0K / 5.4 GB33388262
WhiteRabbitNeo 13B GGUF0K / 5.4 GB894362
Llama 3 13B Instruct V0.1 GGUF0K / 5.1 GB19405
Hermes 2 Pro Llama 3 13B GGUF0K / 4.6 GB1491
Llama3 13B Ku GGUF0K / 8.7 GB520
...aMa 3 Instruct Zeroed 13B GGUF0K / 5 GB421
LLaMa 3 Base Zeroed 13B GGUF0K / 5 GB161
Model10K / 13.8 GB160
Codellama 7B Instruct GGUF0K / 2.8 GB1661
LlaMAndement 13B GGUF0K / 4.8 GB2130
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/NexusRaven-13B-GGUF.