What are the hardware requirements for Amaretto 3B?

Amaretto 3B requires approximately 7.7 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Amaretto 3B and how large is it?

Amaretto 3B is developed by AmarettoLabs, a model with 3b 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 Amaretto 3B?

Amaretto 3B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Amaretto 3B by AmarettoLabs — VRAM 7.7GB

Name: Amaretto 3B
Author: AmarettoLabs

Amaretto 3B is an open-source language model by AmarettoLabs. Features: 3b LLM, VRAM: 7.7GB, License: apache-2.0, Quantized, Instruction-Based, LLM Explorer Score: 0.28.

4bit Base model:mistralai/ministral... Base model:quantized:mistralai... Conversational Creative-writing En Endpoints compatible Finetuned Gguf Instruct Mistral3 Q4 Qlora Quantized Region:us Safetensors Sharded Tensorflow Writing-assistant

Model Card on HF 🤗: https://huggingface.co/AmarettoLabs/Amaretto-3B

Amaretto 3B Parameters and Internals

LLM Name	Amaretto 3B
Repository 🤗	https://huggingface.co/AmarettoLabs/Amaretto-3B
Model Name	unsloth/ministral-3-3b-instruct-2512-unsloth-bnb-4bit
Base Model(s)	Ministral 3 3B Instruct 2512 mistralai/Ministral-3-3B-Instruct-2512
Model Size	3b
Required VRAM	7.7 GB
Updated	2026-08-17
Maintainer	AmarettoLabs
Model Type	mistral3
Instruction-Based	Yes
Model Files	2.1 GB 2.5 GB 2.8 GB 3.6 GB 5.0 GB: 1-of-2 2.7 GB: 2-of-2
Supported Languages	en
GGUF Quantization	Yes
Quantization Type	q4\|4bit\|gguf\|q4_k\|q5_k
Model Architecture	Mistral3ForConditionalGeneration
License	apache-2.0
Model Max Length	262144
Tokenizer Class	TokenizersBackend
Padding Token	<pad>
Torch Data Type	bfloat16

Rank the Amaretto 3B 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 Amaretto 3B

Best Alternatives	Context / RAM	Downloads	Likes
Koa AI V1 Code 3B	0K / 7.7 GB	356	1
...al 3 3B Instruct 2512 Bnb 4bit	0K / 3.2 GB	693	0
...istral 3 3B Instruct 2512 ONNX	0K / GB	436	32
Ministral 3 3B Instruct 2512	0K / 6.8 GB	94	1

Note: green Score (e.g. "73.2") means that the model is better than AmarettoLabs/Amaretto-3B.