What are the hardware requirements for Nanowhale 100M Base?

Nanowhale 100M Base requires approximately 0.4 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 Nanowhale 100M Base and how large is it?

Nanowhale 100M Base is developed by HuggingFaceTB, a model with 100m 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 Nanowhale 100M Base?

Nanowhale 100M Base is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Nanowhale 100M Base by HuggingFaceTB — VRAM 0.4GB, 2K context

Name: Nanowhale 100M Base
Author: HuggingFaceTB

Nanowhale 100M Base is an open-source language model by HuggingFaceTB. Features: 100m LLM, VRAM: 0.4GB, Context: 2K, License: apache-2.0, LLM Explorer Score: 0.26.

Conversational Custom code Dataset:huggingfacefw/fineweb-... Deepseek Deepseek v4 En Endpoints compatible Moe Pretrained Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/HuggingFaceTB/nanowhale-100m-base

Nanowhale 100M Base Parameters and Internals

LLM Name	Nanowhale 100M Base
Repository 🤗	https://huggingface.co/HuggingFaceTB/nanowhale-100m-base
Model Size	100m
Required VRAM	0.4 GB
Updated	2026-08-09
Maintainer	HuggingFaceTB
Model Type	deepseek_v4
Model Files	0.4 GB
Supported Languages	en
Model Architecture	DeepseekV4ForCausalLM
License	apache-2.0
Context Length	2048
Model Max Length	2048
Transformers Version	5.6.2
Tokenizer Class	TokenizersBackend
Padding Token	<｜end▁of▁sentence｜>
Vocabulary Size	129280

Rank the Nanowhale 100M Base 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 Nanowhale 100M Base

Best Alternatives	Context / RAM	Downloads	Likes
Wader 100M Base	2K / 0.4 GB	337	0
Nanowhale 100M	2K / 0.4 GB	552	67

Note: green Score (e.g. "73.2") means that the model is better than HuggingFaceTB/nanowhale-100m-base.