What are the hardware requirements for Nesso3 0.4B Agentic?

Nesso3 0.4B Agentic requires approximately 0.9 GB of VRAM and supports a context window of 32K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Nesso3 0.4B Agentic and how large is it?

Nesso3 0.4B Agentic is developed by mii-llm, a model with 0.4b 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 Nesso3 0.4B Agentic?

Nesso3 0.4B Agentic is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Nesso3 0.4B Agentic by mii-llm — VRAM 0.9GB, 32K context

Name: Nesso3 0.4B Agentic
Author: mii-llm

Nesso3 0.4B Agentic is an open-source language model by mii-llm. Features: 0.4b LLM, VRAM: 0.9GB, Context: 32K, License: apache-2.0, LLM Explorer Score: 0.29.

Agentic Base model:finetune:mii-llm/za... Base model:mii-llm/zagreus-0.4... Bilingual Conversational Dataset:nvidia/when2call Dataset:salesforce/xlam-functi... Dataset:team-ace/toolace Edge-ai En Endpoints compatible Function-calling It Italian Llama Nanotron Region:us Safetensors Slm Small-language-model Structured-output Tool-use Trl

Model Card on HF 🤗: https://huggingface.co/mii-llm/nesso3-0.4B-agentic

Nesso3 0.4B Agentic Parameters and Internals

LLM Name	Nesso3 0.4B Agentic
Repository 🤗	https://huggingface.co/mii-llm/nesso3-0.4B-agentic
Base Model(s)	mii-llm/zagreus-0.4B-ita mii-llm/zagreus-0.4B-ita
Model Size	0.4b
Required VRAM	0.9 GB
Updated	2026-10-19
Maintainer	mii-llm
Model Type	llama
Model Files	0.9 GB
Supported Languages	it en
Model Architecture	LlamaForCausalLM
License	apache-2.0
Context Length	32768
Model Max Length	32768
Transformers Version	5.7.0.dev0
Tokenizer Class	TokenizersBackend
Padding Token	<\|finetune_right_pad_id\|>
Vocabulary Size	128256

Rank the Nesso3 0.4B Agentic 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 Nesso3 0.4B Agentic

Best Alternatives	Context / RAM	Downloads	Likes
Zagreus 0.4B Ita	4K / 0.9 GB	3222	11
Buddy Nesso Sft V1	4K / 0.9 GB	15	0
Nesso 0.4B Agentic	4K / 2.2 GB	585	5
Caracal GPT	2K / 1.3 GB	16	0
...st Size 0.002 Lelapa Mtt Train	2K / 2.7 GB	10	0
... Hausa Dataset Test Size 0.002	2K / 2.7 GB	8	0