What are the hardware requirements for Rose 20B?

Rose 20B requires approximately 39.9 GB of VRAM and supports a context window of 4K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Rose 20B and how large is it?

Rose 20B is developed by tavtav, a model with 20b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Rose 20B?

Rose 20B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Rose 20B by tavtav — VRAM 39.9GB, 4K context

Name: Rose 20B
Author: tavtav

Rose 20B is an open-source language model by tavtav. Features: 20b LLM, VRAM: 39.9GB, Context: 4K, License: llama2, Instruction-Based, LLM Explorer Score: 0.1.

Deploy:azure En Endpoints compatible Instruct Llama Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/tavtav/Rose-20B

Rose 20B Parameters and Internals

Model Type

text-generation

Use Cases

Areas:

Roleplay scenarios

Additional Notes

This model is experiment driven and may be merged with other Frankenmerge models for further capabilities.

Supported Languages

en (fluent)

Training Details

Data Sources:

Thorns-13B, Noromaid-13-v0.1.1

Methodology:

Experimental merging of layers from different models (Frankenmerge)

Input Output

Input Format:

Alpaca format

Accepted Modalities:

text

LLM Name	Rose 20B
Repository 🤗	https://huggingface.co/tavtav/Rose-20B
Model Size	20b
Required VRAM	39.9 GB
Updated	2026-07-21
Maintainer	tavtav
Model Type	llama
Instruction-Based	Yes
Model Files	9.9 GB: 1-of-5 9.9 GB: 2-of-5 9.9 GB: 3-of-5 10.0 GB: 4-of-5 0.2 GB: 5-of-5
Supported Languages	en
Model Architecture	LlamaForCausalLM
License	llama2
Context Length	4096
Model Max Length	4096
Transformers Version	4.36.0.dev0
Tokenizer Class	LlamaTokenizer
Padding Token	[PAD]
Vocabulary Size	32000
Torch Data Type	float16

Rank the Rose 20B capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

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

Quantized Models of the Rose 20B

Model	Likes	Downloads	VRAM
Rose 20B GGUF	29	394	8 GB
Rose Kimiko 20B	2	2	0 GB
Rose 20B GPTQ	3	4	10 GB
Rose 20B AWQ	1	1	10 GB

Best Alternatives to Rose 20B

Best Alternatives	Context / RAM	Downloads	Likes
EAGLE3 GPT Oss 20B	128K / 0.7 GB	507	0
Bagel 20B V04 Llama	32K / 39.6 GB	6	7
Bagel DPO 20B V04 Llama	32K / 39.6 GB	7	3
...lm2 1.7B Distilled GPT Oss 20B	8K / 0 GB	35	3
...runed Base PostPruneRetraining	8K / 0 GB	5	0
...lerLM 20M Instruct Pruned Sft5	8K / 0.1 GB	12	0
...I Llama2 Ko En Instruct 20B V1	2K / 40.4 GB	5	0
Rose 20B GPTQ	4K / 10.5 GB	4	3
Rose 20B AWQ	4K / 10.9 GB	1	1

Note: green Score (e.g. "73.2") means that the model is better than tavtav/Rose-20B.