What are the hardware requirements for Sarashina2.1 1B Sft?

Sarashina2.1 1B Sft requires approximately 2.8 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 Sarashina2.1 1B Sft and how large is it?

Sarashina2.1 1B Sft is developed by Aratako, a model with 1b 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 Sarashina2.1 1B Sft?

Sarashina2.1 1B Sft is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Sarashina2.1 1B Sft by Aratako — VRAM 2.8GB, 8K context

Name: Sarashina2.1 1B Sft
Author: Aratako

Sarashina2.1 1B Sft is an open-source language model by Aratako. Features: 1b LLM, VRAM: 2.8GB, Context: 8K, License: other, LLM Explorer Score: 0.16.

Axolotl Base model:finetune:sbintuitio... Base model:sbintuitions/sarash... Conversational Endpoints compatible Generated from trainer Ja Llama Pytorch Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/Aratako/sarashina2.1-1b-sft

Sarashina2.1 1B Sft Parameters and Internals

LLM Name	Sarashina2.1 1B Sft
Repository 🤗	https://huggingface.co/Aratako/sarashina2.1-1b-sft
Base Model(s)	sbintuitions/sarashina2.1-1b sbintuitions/sarashina2.1-1b
Model Size	1b
Required VRAM	2.8 GB
Updated	2026-08-24
Maintainer	Aratako
Model Type	llama
Model Files	2.8 GB 2.8 GB 0.0 GB
Supported Languages	ja
Model Architecture	LlamaForCausalLM
License	other
Context Length	8192
Model Max Length	8192
Transformers Version	4.46.3
Tokenizer Class	LlamaTokenizer
Padding Token	<pad>
Vocabulary Size	102402
Torch Data Type	bfloat16

Rank the Sarashina2.1 1B Sft 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 Sarashina2.1 1B Sft

Best Alternatives	Context / RAM	Downloads	Likes
ISA 02 Nano Llama 3.2 1B	1024K / 2.5 GB	47	3
LWM Text 1M	1024K / 13.5 GB	1149	29
LWM Text Chat 1M	1024K / 13.5 GB	57	173
JOSIE 1M Base	1024K / 13.5 GB	12	1
JOSIE 1M Base	1024K / 13.5 GB	6	1
MiniCPM5 1B MegaMerge Final	512K / 2.2 GB	0	1
MiniCPM5 1B	128K / 2.2 GB	354385	868
Llama 3.2 1B Instruct	128K / 2.5 GB	212072	100
...1B Claude Opus Fable5 Thinking	128K / 2.2 GB	6165	166
Llama 3.2 1B Instruct	128K / 2.5 GB	10114634	1549

Note: green Score (e.g. "73.2") means that the model is better than Aratako/sarashina2.1-1b-sft.