LLM EXPLORER 59,420 MODELS INDEXED

Rogue Rose 103B V0.2 GGUF by TheBloke

By TheBloke · 120 downloads
HF Repo ↗ Copy URL

Rogue Rose 103B V0.2 GGUF is an open-source language model by TheBloke. Features: 103b LLM, VRAM: 43.5GB, License: llama2, Quantized, LLM Explorer Score: 0.1.

  Arxiv:2307.11760 Base model:quantized:sophosymp... Base model:sophosympatheia/rog...   En   Gguf   Llama   Quantized   Region:us
Model Card on HF 🤗: https://huggingface.co/TheBloke/Rogue-Rose-103b-v0.2-GGUF 

Rogue Rose 103B V0.2 GGUF Parameters and Internals

Model Type 
llama
Use Cases 
Areas:
roleplaying, storytelling
Limitations:
may perform poorly on tasks outside roleplaying and storytelling
Additional Notes 
Frankenmerge of two custom 70b merges. Features 120 layers. Designed for role-playing.
Supported Languages 
en (unknown)
Training Details 
Context Length:
8192
Input Output 
Input Format:
Vicuna instruction format
Performance Tips:
Model tolerates high temperatures with Min-P. Model seems to benefit from higher settings for repetition penalty and presence penalty. Using frequency penalty set to 0.01 is recommended.
LLM NameRogue Rose 103B V0.2 GGUF
Repository 🤗https://huggingface.co/TheBloke/Rogue-Rose-103b-v0.2-GGUF 
Model NameRogue Rose 103B v0.2
Model CreatorSophosympatheia
Base Model(s)  sophosympatheia/Rogue-Rose-103b-v0.2   sophosympatheia/Rogue-Rose-103b-v0.2
Model Size103b
Required VRAM43.5 GB
Updated2026-08-04
MaintainerTheBloke
Model Typellama
Model Files  43.5 GB   49.5 GB   44.5 GB
Supported Languagesen
GGUF QuantizationYes
Quantization Typegguf
Model ArchitectureAutoModel
Licensellama2

Best Alternatives to Rogue Rose 103B V0.2 GGUF

Best Alternatives
Context / RAM
Downloads
Likes
Aurora Nights 103B V1.0 GGUF0K / 43.5 GB23612
Lila 103B L2 GGUF0K / 43.5 GB712
Solus 103B L2 GGUF0K / 43.5 GB400
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Rogue-Rose-103b-v0.2-GGUF.