What are the hardware requirements for Open Calm 7B?

Open Calm 7B requires approximately 13.9 GB of VRAM and supports a context window of 2K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Open Calm 7B and how large is it?

Open Calm 7B is developed by cyberagent, a model with 7b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Open Calm 7B perform on standard benchmarks?

Open Calm 7B has the following published scores: MMLU 25.22. Compare against reference models on this page or on the LLM Explorer leaderboards.

Open Calm 7B by cyberagent — VRAM 13.9GB, 2K context

Name: Open Calm 7B
Author: cyberagent

Open Calm 7B is an open-source language model by cyberagent. Features: 7b LLM, VRAM: 13.9GB, Context: 2K, License: cc-by-sa-4.0, LLM Explorer Score: 0.13, Arc: 20.5, HellaSwag: 30.7, MMLU: 25.2, GSM8K: 0.2.

Dataset:cc100 Dataset:mc4 Dataset:wikipedia Deploy:azure Gpt neox Ja Japanese Pytorch Region:us Sharded

Model Card on HF 🤗: https://huggingface.co/cyberagent/open-calm-7b

Open Calm 7B Parameters and Internals

Model Type

Transformer-based Language Model, causal-lm

Additional Notes

This model is a fine-tuned version of OpenCALM-XX developed by CyberAgent, Inc. The model uses GPT-NeoX, a large-scale autoregressive language modeling library in PyTorch.

Supported Languages

ja (Proficient)

Training Details

Data Sources:

Wikipedia (ja), Common Crawl (ja)

Model Architecture:

Decoder-only

LLM Name	Open Calm 7B
Repository 🤗	https://huggingface.co/cyberagent/open-calm-7b
Model Size	7b
Required VRAM	13.9 GB
Updated	2026-07-21
Maintainer	cyberagent
Model Type	gpt_neox
Model Files	9.9 GB: 1-of-2 4.0 GB: 2-of-2
Supported Languages	ja
Model Architecture	GPTNeoXForCausalLM
License	cc-by-sa-4.0
Context Length	2048
Model Max Length	2048
Transformers Version	4.27.0.dev0
Tokenizer Class	GPTNeoXTokenizer
Padding Token	<\|padding\|>
Vocabulary Size	52224
Torch Data Type	float16

Rank the Open Calm 7B 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 Open Calm 7B

Best Alternatives	Context / RAM	Downloads	Likes
Literature 7B 16384	16K / 36 GB	9	16
RedPajama 7B 16384	16K / 36 GB	8	4
Stablelm Tuned Alpha 7B	4K / 31.9 GB	713	361
Stablelm Base Alpha 7B	4K / 31.9 GB	884	208
Stablelm 7B Sft V7 Epoch 3	4K / 32.4 GB	64	67
StableLManticore 7B	4K / 16 GB	10	1
Pythia 6.9B Deduped 4K	4K / 27.2 GB	8	10
Stablelm 7B	4K / 31.9 GB	7	2
Dolly V2 7B	2K / 13.8 GB	1596	150
Sarashina1 7B	2K / 13.9 GB	11	1

Note: green Score (e.g. "73.2") means that the model is better than cyberagent/open-calm-7b.