PR

PRO 2

ProGGUF by realProAIUpdated 2026-10-11
Download on Hugging Face
Parameters2.32B
Context32K
Layers32
Architecturellama
Smallest quant2.0 GB
Quick answer

PRO 2 needs about 3.6 GB of memory at its main file (a 2.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

PRO 2 – 2.32B llama model with 32,768 token context

PRO 2 is a 2.32 billion parameter llama model. It supports a 32,768 token context window and includes tools capability. The model is released under the Apache‑2.0 license.

Good at

  • Large context handling
  • Tool usage
  • Apache‑2.0 licensed

Limits

  • No vision support
  • Only one quant available
  • Requires 3.6 GB VRAM at 8k context

Best for

  • Long‑form content generation
  • Complex tool‑based workflows
  • Projects needing large context

Who it’s for. Developers and researchers who need a large‑context llama model with tool integration and an open license. Suitable for applications that can run the single available quant on a GPU with at least 4 GB VRAM.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—2.0 GB 3.6 GB
Fits Get file →

The only quant available is the unknown quant with a file size of 2.02 GB. It requires approximately 3.6 GB VRAM at 8k context. For systems with 4 GB or more VRAM, this quant is recommended. No other quants are provided.

What GPU do you need for PRO 2?

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 (2.0 GB file, about 3.6 GB in use).

Specifications

Architecture from the GGUF header

Architecturellama
Parameters2.32B
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized byrealProAI
FamilyPro
RepositoryrealProAI/PRO-2
Licenseapache-2.0
Downloads (HF)695
Last updated2026-10-11

Frequently asked questions about PRO 2

How much VRAM does PRO 2 need?

About 3.6 GB at its main file with an 8K context window. That is the 2.0 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 PRO 2 on an 8 GB GPU?

Yes, with the smaller files: the 2.0 GB file needs about 3.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of PRO 2 GGUF?

It depends on the quant: file is 2.0 GB.

What context length does PRO 2 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download PRO 2 GGUF?

The files are on Hugging Face in the realProAI/PRO-2 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does PRO 2 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 PRO 2 on 8 GB VRAM?

Yes, the single quant requires about 3.6 GB VRAM at 8k context, leaving room for other processes.

Does PRO 2 support vision?

No, the model has no vision capability.

Similar models

Browse all →

More Pro models

All Pro →

Other tiny models

All tiny models →