What are the hardware requirements for Instella 3B Math?

Instella 3B Math requires approximately 6.2 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 Instella 3B Math and how large is it?

Instella 3B Math is developed by amd, 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 Instella 3B Math?

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

Instella 3B Math by amd — VRAM 6.2GB, 32K context

Name: Instella 3B Math
Author: amd

Instella 3B Math is an open-source language model by amd. Features: 3b LLM, VRAM: 6.2GB, Context: 32K, License: other, Instruction-Based, LLM Explorer Score: 0.2.

Arxiv:2506.10209 Arxiv:2511.10628 Base model:amd/instella-3b-ins... Base model:finetune:amd/instel... Conversational Custom code Dataset:a-m-team/am-deepseek-r... Dataset:agentica-org/deepscale... Dataset:nvidia/openmathinstruc... Dataset:synthlabsai/big-math-r... Dataset:zwhe99/deepmath-103k En Instella Instruct Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/amd/Instella-3B-Math

Instella 3B Math Parameters and Internals

LLM Name	Instella 3B Math
Repository 🤗	https://huggingface.co/amd/Instella-3B-Math
Base Model(s)	Instella 3B Instruct amd/Instella-3B-Instruct
Model Size	3b
Required VRAM	6.2 GB
Updated	2026-08-09
Maintainer	amd
Model Type	instella
Instruction-Based	Yes
Model Files	5.0 GB: 1-of-2 1.2 GB: 2-of-2
Supported Languages	en
Model Architecture	InstellaForCausalLM
License	other
Context Length	32768
Model Max Length	32768
Transformers Version	4.51.3
Tokenizer Class	GPTNeoXTokenizer
Padding Token	<\|padding\|>
Vocabulary Size	50304
Torch Data Type	bfloat16

Rank the Instella 3B Math 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 Instella 3B Math

Best Alternatives	Context / RAM	Downloads	Likes
Instella 3B Long Instruct	128K / 6.2 GB	18	5
Instella 3B Instruct	4K / 6.2 GB	261	59