Tiny Lm Japanese 500M Base V1 is an open-source language model by nagohachi. Features: 500m LLM, VRAM: 1GB, Context: 2K, LLM Explorer Score: 0.28.
Custom code Dataset:hotchpotch/fineweb-2-e... Ja Japanese Llama Pretrained Region:us Safetensors Scratch llama
Model Card on HF 🤗: https://huggingface.co/nagohachi/tiny-lm-japanese-500m-base-v1
Tiny Lm Japanese 500M Base V1 Benchmarks
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 Base V1 Parameters and Internals
| LLM Name | Tiny Lm Japanese 500M Base V1 |
| Repository 🤗 | https://huggingface.co/nagohachi/tiny-lm-japanese-500m-base-v1 |
| Model Size | 500m |
| Required VRAM | 1 GB |
| Updated | 2026-07-23 |
| Maintainer | nagohachi |
| Model Type | scratch_llama |
| Model Files | |
| 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 Base 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! 🌟
What open-source LLMs or SLMs are you in search of? 55346 in total.
Original data from HuggingFace, Arena and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a