What are the hardware requirements for Tiny Lm Japanese 500M Sft V1?

Tiny Lm Japanese 500M Sft V1 requires approximately 1 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 Tiny Lm Japanese 500M Sft V1 and how large is it?

Tiny Lm Japanese 500M Sft V1 is developed by nagohachi, 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 Tiny Lm Japanese 500M Sft V1?

Tiny Lm Japanese 500M Sft V1 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Tiny Lm Japanese 500M Sft V1 by nagohachi — VRAM 1GB, 2K context

Name: Tiny Lm Japanese 500M Sft V1
Author: nagohachi

Tiny Lm Japanese 500M Sft V1 is an open-source language model by nagohachi. Features: 22b LLM, VRAM: 1GB, Context: 2K, LLM Explorer Score: 0.28.

Base model:finetune:nagohachi/... Base model:nagohachi/tiny-lm-j... Chat Conversational Custom code Dataset:kanhatakeyama/automult... Dataset:llm-jp/magpie-sft-v1.0 Ja Japanese Llama Region:us Safetensors Scratch llama Sft

Model Card on HF 🤗: https://huggingface.co/nagohachi/tiny-lm-japanese-500m-sft-v1

Tiny Lm Japanese 500M Sft V1 Benchmarks

LLME Score: 0.27727

^nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

What is the LLM Explorer Rank (Score)

Tiny Lm Japanese 500M Sft V1 (nagohachi/tiny-lm-japanese-500m-sft-v1)

Tiny Lm Japanese 500M Sft V1 Parameters and Internals

LLM Name	Tiny Lm Japanese 500M Sft V1
Repository 🤗	https://huggingface.co/nagohachi/tiny-lm-japanese-500m-sft-v1
Base Model(s)	Tiny Lm Japanese 500M Base V1 nagohachi/tiny-lm-japanese-500m-base-v1
Model Size	22b
Required VRAM	1 GB
Updated	2026-07-23
Maintainer	nagohachi
Model Type	scratch_llama
Model Files	1.0 GB
Supported Languages	ja
Model Architecture	ScratchLlamaForCausalLM
Context Length	2048
Model Max Length	2048
Transformers Version	5.14.1
Tokenizer Class	TokenizersBackend
Padding Token	<PAD\|LLM-jp>
Vocabulary Size	99574

Rank the Tiny Lm Japanese 500M Sft V1 Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

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

What open-source LLMs or SLMs are you in search of? 55346 in total.

Email us: info@extractum.io. Our Privacy Policy | Terms and Conditions | Suggest an improvement.

Our Social Media →

Original data from HuggingFace, Arena and various public git repos.

Check out Ag3ntum — our secure, self-hosted AI agent for server management.

Release v20260328a

Support LLM Explorer

Tiny Lm Japanese 500M Sft V1 by nagohachi

» All LLMs » nagohachi » Tiny Lm Japanese 500M Sft V1 URL Share it on

Tiny Lm Japanese 500M Sft V1 Benchmarks

Tiny Lm Japanese 500M Sft V1 Parameters and Internals

Rank the Tiny Lm Japanese 500M Sft V1 Capabilities

What open-source LLMs or SLMs are you in search of? 55346 in total.