LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  Agents   Benchmarks   LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Rose 20B AWQ by TheBloke

 »  All LLMs  »  TheBloke  »  Rose 20B AWQ   URL Share it on

  4   

Rose 20B AWQ is an open-source language model by TheBloke. Features: 20b LLM, VRAM: 10.9GB, Context: 4K, License: llama2, Quantized, Instruction-Based, LLM Explorer Score: 0.11.

  4-bit   Awq Base model:quantized:tavtav/ro...   Base model:tavtav/rose-20b   En   Instruct   Llama   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/TheBloke/Rose-20B-AWQ 

Rose 20B AWQ Benchmarks

LLME Score: 0.10555
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Rose 20B AWQ (TheBloke/Rose-20B-AWQ)
🌟 Advertise your project 🚀

Rose 20B AWQ Parameters and Internals

Model Type 
llama
Additional Notes 
This model is very robust and recommended for roleplay scenarios. Intended for future fine-tuning experiments.
Supported Languages 
en (native)
Training Details 
Methodology:
Frankenmerge with Thorns-13B by CalderaAI and Noromaid-13-v0.1.1 by NeverSleep.
Model Architecture:
Frankenmerge model
Input Output 
Input Format:
Alpaca template: Below is an instruction that describes a task. Write a response that appropriately completes the request. ### Instruction: {prompt} ### Response:
Accepted Modalities:
text generation
LLM NameRose 20B AWQ
Repository 🤗https://huggingface.co/TheBloke/Rose-20B-AWQ 
Model NameRose 20B
Model CreatorTav
Base Model(s)  Rose 20B   tavtav/Rose-20B
Model Size20b
Required VRAM10.9 GB
Updated2026-04-06
MaintainerTheBloke
Model Typellama
Instruction-BasedYes
Model Files  10.0 GB: 1-of-2   0.9 GB: 2-of-2
Supported Languagesen
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length4096
Model Max Length4096
Transformers Version4.35.2
Tokenizer ClassLlamaTokenizer
Padding Token[PAD]
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Rose 20B AWQ

Best Alternatives
Context / RAM
Downloads
Likes
Bagel 20B V04 Llama32K / 39.6 GB207
Bagel DPO 20B V04 Llama32K / 39.6 GB53
...lm2 1.7B Distilled GPT Oss 20B8K / 0 GB252
...runed Base PostPruneRetraining8K / 0 GB50
...lerLM 20M Instruct Pruned Sft58K / 0.1 GB60
Rose 20B4K / 39.9 GB74345
Rose 20B GPTQ4K / 10.5 GB5973
...I Llama2 Ko En Instruct 20B V12K / 40.4 GB50
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Rose-20B-AWQ.

Rank the Rose 20B AWQ Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 52721 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer