What are the hardware requirements for Pleias RAG 350M?

Pleias RAG 350M requires approximately 0.7 GB of VRAM and supports a context window of 4K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Pleias RAG 350M and how large is it?

Pleias RAG 350M is developed by PleIAs, a model with 350m 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 Pleias RAG 350M?

Pleias RAG 350M is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Pleias RAG 350M by PleIAs — VRAM 0.7GB, 4K context

Name: Pleias RAG 350M
Author: PleIAs

Pleias RAG 350M is an open-source language model by PleIAs. Features: 350m LLM, VRAM: 0.7GB, Context: 4K, License: apache-2.0, LLM Explorer Score: 0.18.

Arxiv:2504.18225 Base model:finetune:pleias/ple... Base model:pleias/pleias-350m-... De Deploy:azure En Endpoints compatible Es Fr It Llama Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/PleIAs/Pleias-RAG-350M

Pleias RAG 350M Parameters and Internals

LLM Name	Pleias RAG 350M
Repository 🤗	https://huggingface.co/PleIAs/Pleias-RAG-350M
Base Model(s)	Pleias 350M Preview PleIAs/Pleias-350m-Preview
Model Size	350m
Required VRAM	0.7 GB
Updated	2026-08-08
Maintainer	PleIAs
Model Type	llama
Model Files	0.7 GB
Supported Languages	en fr it de es
Model Architecture	LlamaForCausalLM
License	apache-2.0
Context Length	4096
Model Max Length	4096
Transformers Version	4.44.2
Tokenizer Class	PreTrainedTokenizerFast
Vocabulary Size	65536
Torch Data Type	bfloat16

Rank the Pleias RAG 350M 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 Pleias RAG 350M

Best Alternatives	Context / RAM	Downloads	Likes
Llama 350M	16K / 0.7 GB	0	0
Atom 350M	8K / 0.7 GB	19	2
... Model On 350B GneissWeb.seed3	8K / 27.4 GB	71	1
... Model On 350B GneissWeb.seed2	8K / 27.4 GB	63	1
...on Model On 350B FineWeb.seed3	8K / 27.4 GB	57	1
...on Model On 350B FineWeb.seed1	8K / 27.4 GB	68	1
...on Model On 350B FineWeb.seed2	8K / 27.4 GB	23	1
...odel On 350B FineWeb.Edu.seed2	8K / 27.4 GB	23	1
...odel On 350B FineWeb.Edu.seed1	8K / 27.4 GB	58	1
...odel On 350B FineWeb.Edu.seed3	8K / 27.4 GB	6	1

Note: green Score (e.g. "73.2") means that the model is better than PleIAs/Pleias-RAG-350M.