What are the hardware requirements for Salamandra 2B Instruct?

Salamandra 2B Instruct requires approximately 4.5 GB of VRAM and supports a context window of 8K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Salamandra 2B Instruct and how large is it?

Salamandra 2B Instruct is developed by BSC-LT, a model with 2b 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 Salamandra 2B Instruct?

Salamandra 2B Instruct is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Salamandra 2B Instruct by BSC-LT — VRAM 4.5GB, 8K context

Name: Salamandra 2B Instruct
Author: BSC-LT

Salamandra 2B Instruct is an open-source language model by BSC-LT. Features: 2b LLM, VRAM: 4.5GB, Context: 8K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.17.

Arxiv:1803.09010 Arxiv:1810.06694 Arxiv:1906.03741 Arxiv:1911.05507 Arxiv:2101.00027 Arxiv:2207.00220 Arxiv:2402.06619 Arxiv:2403.14009 Arxiv:2403.20266 Arxiv:2406.17557 Arxiv:2502.08489 Base model:bsc-lt/salamandra-2... Base model:finetune:bsc-lt/sal... Bg Ca Code Conversational Cs Cy Da Dataset:ai-team-uoa/greek lega... Dataset:allenai/pes2o Dataset:bigcode/starcoderdata Dataset:bjoernp/tagesschau-201... Dataset:community-datasets/hrw... Dataset:danish-foundation-mode... Dataset:eleutherai/the pile de... Dataset:hitz/euscrawl Dataset:hitz/latxa-corpus-v1.1 Dataset:hoskinson-center/proof... Dataset:huggingfacefw/fineweb-... Dataset:joelito/legal-mc4 Dataset:joelniklaus/eurlex res... Dataset:oscar-corpus/colossal-... Dataset:pile-of-law/pile-of-la... Dataset:pleias/french-pd-books Dataset:pleias/french-pd-newsp... Dataset:portulan/parlamento-pt Dataset:projecte-aina/catalog Dataset:togethercomputer/redpa... Dataset:ufrgs/brwac De Deploy:azure El En Endpoints compatible Es Et Eu Fi Fr Ga Gl Hr Hu Instruct It Llama Lt Lv Mt Nl Nn Oc Pl Pt Region:us Ro Ru Safetensors Sh Sk Sl Sr Sv Uk

Model Card on HF 🤗: https://huggingface.co/BSC-LT/salamandra-2b-instruct

Salamandra 2B Instruct Parameters and Internals

LLM Name	Salamandra 2B Instruct
Repository 🤗	https://huggingface.co/BSC-LT/salamandra-2b-instruct
Base Model(s)	Salamandra 2B BSC-LT/salamandra-2b
Model Size	2b
Required VRAM	4.5 GB
Updated	2026-08-25
Maintainer	BSC-LT
Model Type	llama
Instruction-Based	Yes
Model Files	4.5 GB
Supported Languages	bg ca code cs cy da de el en es et eu fi fr ga gl hr hu it lt lv mt nl nn oc pl pt ro ru sh sk sl sr sv uk
Model Architecture	LlamaForCausalLM
License	apache-2.0
Context Length	8192
Model Max Length	8192
Transformers Version	4.40.2
Tokenizer Class	LlamaTokenizer
Padding Token	<unk>
Vocabulary Size	256000
Torch Data Type	bfloat16

Rank the Salamandra 2B Instruct 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 Salamandra 2B Instruct

Best Alternatives	Context / RAM	Downloads	Likes
Aitana 2B SI Instruct	8K / 4.5 GB	52	0
Aitana 2B SI Instruct Aligned	8K / 4.5 GB	19	0
Aitana 2B S IP Instruct	8K / 4.5 GB	13	0
Aitana 2B S Instruct Aligned	8K / 6.9 GB	10	0
Salamandra 2B Fft Trenes	8K / 4.5 GB	32	0
SmolLM2 MedIT Upscale 2B	8K / 4.2 GB	6	5
Llama3 2B Base	8K / 4.7 GB	8	1

Note: green Score (e.g. "73.2") means that the model is better than BSC-LT/salamandra-2b-instruct.