What are the hardware requirements for Calm3 22B RP V2?

Calm3 22B RP V2 requires approximately 44.9 GB of VRAM and supports a context window of 16K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Calm3 22B RP V2 and how large is it?

Calm3 22B RP V2 is developed by Aratako, a model with 22b 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 Calm3 22B RP V2?

Calm3 22B RP V2 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Calm3 22B RP V2 by Aratako — VRAM 44.9GB, 16K context

Name: Calm3 22B RP V2
Author: Aratako

Calm3 22B RP V2 is an open-source language model by Aratako. Features: 22b LLM, VRAM: 44.9GB, Context: 16K, License: cc-by-nc-sa-4.0, LLM Explorer Score: 0.14.

Base model:cyberagent/calm3-22... Base model:finetune:cyberagent... Conversational Dataset:aratako/rosebleu-1on1-... Dataset:aratako/synthetic-japa... Dataset:aratako/synthetic-japa... Dataset:chaser-cz/roleplay scr... Dataset:grimulkan/limarp-augme... Dataset:minervaai/aesir-previe... Dataset:openerotica/freedom-rp Dataset:openerotica/lima-nsfw Dataset:roleplay4fun/aesir-v1.... Dataset:sicariussicariistuff/b... Endpoints compatible Ja Llama Region:us Safetensors Sft Sharded Tensorflow Trl Unsloth

Model Card on HF 🤗: https://huggingface.co/Aratako/calm3-22b-RP-v2

Calm3 22B RP V2 Parameters and Internals

LLM Name	Calm3 22B RP V2
Repository 🤗	https://huggingface.co/Aratako/calm3-22b-RP-v2
Base Model(s)	Calm3 22B Chat cyberagent/calm3-22b-chat
Model Size	22b
Required VRAM	44.9 GB
Updated	2026-08-25
Maintainer	Aratako
Model Type	llama
Model Files	4.9 GB: 1-of-10 4.9 GB: 2-of-10 4.8 GB: 3-of-10 4.9 GB: 4-of-10 5.0 GB: 5-of-10 4.8 GB: 6-of-10 4.9 GB: 7-of-10 4.8 GB: 8-of-10 4.9 GB: 9-of-10 1.0 GB: 10-of-10
Supported Languages	ja
Model Architecture	LlamaForCausalLM
License	cc-by-nc-sa-4.0
Context Length	16384
Model Max Length	16384
Transformers Version	4.44.2
Tokenizer Class	GPTNeoXTokenizer
Padding Token	<\|padding\|>
Vocabulary Size	65024
Torch Data Type	bfloat16

Rank the Calm3 22B RP V2 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 Calm3 22B RP V2

Best Alternatives	Context / RAM	Downloads	Likes
EuroLLM 22B Instruct 2512	32K / 45.5 GB	3342	63
EuroLLM 22B 2512	32K / 45.5 GB	2766	19
Calm3 22B Chat	16K / 44.9 GB	878	85
Calm3 22B RP V0.1	16K / 44.9 GB	10	0
Yousei 22B	4K / 44.5 GB	97	2
Llama2 22B Daydreamer V3	4K / 43.7 GB	177	11
Platypus 2 22B Relora	4K / 43.7 GB	93	1
Llama2 22B Blocktriangular	4K / 43.7 GB	368	4
Llama2 22B	4K / 43.7 GB	109	46
Llama2 22B Daydreamer V2	4K / 43.7 GB	7	2

Note: green Score (e.g. "73.2") means that the model is better than Aratako/calm3-22b-RP-v2.