What are the hardware requirements for C4ai Command R V01 Japanese Instruct?

C4ai Command R V01 Japanese Instruct requires approximately 69.5 GB of VRAM and supports a context window of 8K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed C4ai Command R V01 Japanese Instruct and how large is it?

C4ai Command R V01 Japanese Instruct is developed by Aratako, a model with 35b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does C4ai Command R V01 Japanese Instruct perform on standard benchmarks?

C4ai Command R V01 Japanese Instruct has the following published scores: MMLU 67.61. Compare against reference models on this page or on the LLM Explorer leaderboards.

C4ai Command R V01 Japanese Instruct by Aratako — VRAM 69.5GB, 8K context

Name: C4ai Command R V01 Japanese Instruct
Author: Aratako

C4ai Command R V01 Japanese Instruct is an open-source language model by Aratako. Features: 35b LLM, VRAM: 69.5GB, Context: 8K, License: cc-by-nc-sa-4.0, Instruction-Based, LLM Explorer Score: 0.13, Arc: 65.9, HellaSwag: 85.6, MMLU: 67.6, GSM8K: 60.1.

Base model:coherelabs/c4ai-com... Base model:finetune:coherelabs... Cohere En Endpoints compatible Instruct Ja Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/Aratako/c4ai-command-r-v01-japanese-instruct

C4ai Command R V01 Japanese Instruct Parameters and Internals

Model Type

text generation

Supported Languages

ja (Japanese), en (English)

Training Details

Data Sources:

ichikara-instruction

Methodology:

Japanese instruction fine-tuning

Context Length:

2048

Hardware Used:

A6000 GPU x4

LLM Name	C4ai Command R V01 Japanese Instruct
Repository 🤗	https://huggingface.co/Aratako/c4ai-command-r-v01-japanese-instruct
Base Model(s)	CohereForAI/c4ai-command-r-v01 CohereForAI/c4ai-command-r-v01
Model Size	35b
Required VRAM	69.5 GB
Updated	2026-08-24
Maintainer	Aratako
Model Type	cohere
Instruction-Based	Yes
Model Files	4.7 GB: 1-of-15 4.9 GB: 2-of-15 4.9 GB: 3-of-15 4.9 GB: 4-of-15 4.9 GB: 5-of-15 4.9 GB: 6-of-15 4.9 GB: 7-of-15 4.9 GB: 8-of-15 4.9 GB: 9-of-15 4.9 GB: 10-of-15 4.9 GB: 11-of-15 4.9 GB: 12-of-15 4.9 GB: 13-of-15 4.9 GB: 14-of-15 1.1 GB: 15-of-15
Supported Languages	ja en
Model Architecture	CohereForCausalLM
License	cc-by-nc-sa-4.0
Context Length	8192
Model Max Length	8192
Transformers Version	4.39.3
Tokenizer Class	CohereTokenizer
Padding Token	<PAD>
Vocabulary Size	256000
Torch Data Type	bfloat16

Rank the C4ai Command R V01 Japanese Instruct 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 C4ai Command R V01 Japanese Instruct

Best Alternatives	Context / RAM	Downloads	Likes
35B Beta2ep	8K / 69.5 GB	20	19
35B Beta Long	8K / 69.5 GB	24	69

Note: green Score (e.g. "73.2") means that the model is better than Aratako/c4ai-command-r-v01-japanese-instruct.