BI

bitvla libero

BitvlaGGUF by vrfaiUpdated 2026-06-03
Download on Hugging Face
Parameters1.03B
Context—
Layers—
Architecturebitvla
Smallest quant1.4 GB
Quick answer

bitvla libero needs about 2.1 GB of memory at its main file (a 1.4 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 1.4 GB to 1.4 GB.

1.03B‑parameter BitVLA for vision‑language tasks

BitVLA Libero is a 1.03‑billion‑parameter vision‑language‑action model. It combines a BitSigLIP‑L vision tower with a 30‑layer BitNet language model and a regression head. The GGUF file is 1.44 GB and requires about 2.1 GB of VRAM at 8 k context.

Good at

  • Vision‑language inference
  • Action‑based regression
  • Lightweight deployment

Limits

  • No separate mmproj file needed
  • Requires 8 k context for best performance
  • MIT license only

Best for

  • Embedded vision‑language apps
  • Jetson GPU inference
  • Rapid prototyping

Who it’s for. Developers building lightweight vision‑language systems who need a single GGUF file without extra components. The model is suitable for edge devices and GPU‑based inference engines like vla.cpp.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—1.4 GB 2.1 GB
Fits Get file →
—1.4 GB 2.1 GB
Fits Get file →
—1.4 GB 2.1 GB
Fits Get file →
—1.4 GB 2.1 GB
Fits Get file →

All available GGUF files are 1.44 GB with 2.1 GB VRAM at 8 k context. For 8 GB VRAM, the model fits comfortably. No additional quant options are listed.

What GPU do you need for bitvla libero?

These figures add the file size, an fp16 KV cache at an 8K context window 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 (1.4 GB file, about 2.1 GB in use).

Which bitvla libero quant should you choose?

If memory is tight, the smallest file is the first one in the table at 1.4 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturebitvla
Parameters1.03B

Source

Quantized byvrfai
FamilyBitvla
Licensemit
Downloads (HF)1,450
Last updated2026-06-03

Frequently asked questions about bitvla libero

How much VRAM does bitvla libero need?

About 2.1 GB at its main file with an 8K context window. That is the 1.4 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 bitvla libero on an 8 GB GPU?

Yes, with the smaller files: the 1.4 GB file needs about 2.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of bitvla libero GGUF?

It depends on the quant: file is 1.4 GB, file is 1.4 GB, file is 1.4 GB, file is 1.4 GB.

Where can I download bitvla libero GGUF?

The files are on Hugging Face in the vrfai/bitvla-libero-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 bitvla libero use?

Hugging Face lists the license as mit. 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 BitVLA on 8 GB VRAM?

Yes. The 1.44 GB GGUF requires about 2.1 GB VRAM at 8 k context, well within an 8 GB budget.

Does BitVLA need a separate mmproj file?

No. The vision tower is baked into the combined GGUF, so no mmproj file is required.

What license applies to BitVLA?

The model weights follow the MIT license of the upstream repo, and the conversion tooling is MIT‑licensed.

Similar models

Browse all →

More from vrfai

All by vrfai →

More Bitvla models

All Bitvla →

Other tiny models

All tiny models →