What are the hardware requirements for Rose Kimiko 20B GPTQ?

Rose Kimiko 20B GPTQ requires approximately 10.5 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 Kimiko 20B GPTQ and how large is it?

Rose Kimiko 20B GPTQ is developed by TheBloke, 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 Kimiko 20B GPTQ?

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

Rose Kimiko 20B GPTQ by TheBloke — VRAM 10.5GB, 4K context

Name: Rose Kimiko 20B GPTQ
Author: TheBloke

Rose Kimiko 20B GPTQ is an open-source language model by TheBloke. Features: 20b LLM, VRAM: 10.5GB, Context: 4K, License: llama2, Quantized, LLM Explorer Score: 0.1.

4-bit Base model:adapter:chat-error/... Base model:chat-error/rose-kim... Fp16 Generated from trainer Gptq Llama Peft Quantized Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/TheBloke/Rose-Kimiko-20B-GPTQ

Rose Kimiko 20B GPTQ Parameters and Internals

Model Type

llama

Use Cases

Limitations:

The LoRA is intended to fix spelling from Rose 20B.

Additional Notes

Per many people's requests, this LoRA is intended to fix spelling from Rose 20B.

Training Details

Model Architecture:

The prompt formats used is ShareGPT/Vicuna format.

Input Output

Input Format:

Below is an instruction that describes a task. Write a response that appropriately completes the request. ### Instruction: {prompt} ### Response:

LLM Name	Rose Kimiko 20B GPTQ
Repository 🤗	https://huggingface.co/TheBloke/Rose-Kimiko-20B-GPTQ
Model Name	Rose Kimiko 20B
Model Creator	nRuaif
Base Model(s)	nRuaif/Rose-Kimiko-20B nRuaif/Rose-Kimiko-20B
Model Size	20b
Required VRAM	10.5 GB
Updated	2026-08-01
Maintainer	TheBloke
Model Type	llama
Model Files	10.5 GB
GPTQ Quantization	Yes
Quantization Type	fp16\|gptq
Model Architecture	LlamaForCausalLM
License	llama2
Context Length	4096
Model Max Length	4096
Transformers Version	4.35.2
Tokenizer Class	LlamaTokenizer
Padding Token	[PAD]
Vocabulary Size	32000
Torch Data Type	float16

Rank the Rose Kimiko 20B GPTQ 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

Best Alternatives to Rose Kimiko 20B GPTQ

Best Alternatives	Context / RAM	Downloads	Likes
Norocetacean 20B 10K GPTQ	10K / 10.5 GB	9	2
Orca2myth7.2 GPTQ	4K / 10.9 GB	7	4
DaringMaid 20B GPTQ	4K / 10.5 GB	5	5
Nethena 20B Glued GPTQ	4K / 10.5 GB	5	1
Iambe Storyteller 20B GPTQ	4K / 10.5 GB	4	2
Iambe 20B DARE GPTQ	4K / 10.5 GB	4	1
Noromaid 20B V0.1.1 GPTQ	4K / 10.5 GB	11	8
Rose 20B GPTQ	4K / 10.5 GB	4	3
Nethena 20B GPTQ	4K / 10.5 GB	12	7
MXLewd L2 20B GPTQ	4K / 10.5 GB	8	9

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