PL

Pleias RAG 1B

PleiasGGUF by PleIAsUpdated 2025-04-24
Download on Hugging Face
Parameters1.2B
Context4K
Layers22
Architecturellama
Smallest quant2.4 GB
Quick answer

Pleias RAG 1B needs about 3.3 GB of memory at its main file (a 2.4 GB file) with an 8K context window, so it fits on a 4 GB GPU.

Pleias RAG 1B – a 1.2B‑parameter retrieval‑augmented small reasoning model

Pleias RAG 1B is a 1.2 billion parameter small reasoning model trained for retrieval‑augmented general tasks, search, and source summarization. It is part of the first generation of Pleias specialized reasoning models and is competitive with larger 7‑8B models on RAG benchmarks.

Good at

  • Retrieval‑augmented general QA
  • Search and source summarization
  • Consistent RAG performance across European languages

Limits

  • No vision support
  • Limited to 4096 token context
  • Requires 3.3 GB VRAM at 8k context

Best for

  • Building lightweight RAG applications
  • Deploying on mobile or edge devices
  • Creating accurate source‑grounded content

Who it’s for. Developers needing a small, fact‑centric model for retrieval‑augmented tasks. Researchers exploring efficient RAG solutions on constrained hardware.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—2.4 GB 3.1 GB
Fits Get file →

The available GGUF file is 2.39 GB and needs about 3.3 GB VRAM at 8k context. This is suitable for systems with 4 GB or more VRAM. No other quantizations are provided.

What GPU do you need for Pleias RAG 1B?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: the best quant that fits is the main file (2.4 GB file, about 3.3 GB in use).

Specifications

Architecture from the GGUF header

Architecturellama
Parameters1.2B
Layers22
Trained context4,096 tokens
KV cache (fp16)44 KB per token

Source

Quantized byPleIAs
FamilyPleias
Licenseapache-2.0
Downloads (HF)597
Last updated2025-04-24

Frequently asked questions about Pleias RAG 1B

How much VRAM does Pleias RAG 1B need?

About 3.3 GB at its main file with an 8K context window. That is the 2.4 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run Pleias RAG 1B on an 8 GB GPU?

Yes, with the smaller files: the 2.4 GB file needs about 3.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Pleias RAG 1B GGUF?

It depends on the quant: file is 2.4 GB.

What context length does Pleias RAG 1B support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 0.4 GB at 8K and 0.2 GB at 4K.

Where can I download Pleias RAG 1B GGUF?

The files are on Hugging Face in the PleIAs/Pleias-RAG-1B-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Pleias RAG 1B use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run Pleias RAG 1B on 4 GB VRAM?

Yes, the model requires approximately 3.3 GB VRAM at 8k context, which fits within a 4 GB VRAM budget.

Does Pleias RAG 1B support image inputs?

No, the model has no vision capabilities.

Similar models

Browse all →

More from PleIAs

All by PleIAs →

More Pleias models

All Pleias →

Other tiny models

All tiny models →