WI

Wizard Orca 3B

WizardGGUF by AryanneUpdated 2023-10-07
Download on Hugging Face
Parameters3.43B
Context2K
Layers26
Architecturellama
Smallest quant2.0 GB
Quick answer

Wizard Orca 3B needs about 5.4 GB of memory at Q4_1 (a 2.2 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 4 quants, from 2.0 GB (Q4_0) to 2.6 GB (Q5_1).

Wizard Orca 3B – 3.43B llama architecture model

Wizard Orca 3B is a 3.43B parameter llama model trained on 2 epochs of the WizardLM_orca dataset. It is available in several GGUF v2 quantizations and licensed under Apache‑2.0.

Good at

  • Small‑to‑medium context generation
  • Fast inference on modest GPUs
  • Low‑memory deployment

Limits

  • No vision support
  • Limited to 2048 token context
  • Requires at least 5.2 GB VRAM for Q4_0

Best for

  • Chatbot prototypes
  • Rapid prototyping of text generation
  • Low‑cost inference on consumer GPUs

Who it’s for. Developers and researchers needing a lightweight llama model with open‑source licensing. Suitable for projects that require quick deployment and moderate context lengths.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_02.0 GB 3.2 GB
Fits Get file →
Q4_12.2 GB 3.4 GB
Fits Get file →
Q5_02.4 GB 3.6 GB
Fits Get file →
Q5_12.6 GB 3.8 GB
Fits Get file →

For 8 GB VRAM, Q4_0 (1.98 GB) or Q4_1 (2.19 GB) are recommended; they need about 5.2–5.4 GB VRAM at 8 k context. If more memory is available, Q5_0 or Q5_1 offer higher precision with 5.6–5.8 GB VRAM usage.

What GPU do you need for Wizard Orca 3B?

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: no quant fits at an 8K context.
  • 6 GB VRAM: the best quant that fits is Q5_1 (2.6 GB file, about 5.8 GB in use).

Which Wizard Orca 3B quant should you choose?

Q4_1 (2.2 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

If memory is tight, the smallest file is Q4_0 at 2.0 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters3.43B
Layers26
Trained context2,048 tokens
KV cache (fp16)325 KB per token

Source

Quantized byAryanne
FamilyWizard
Licenseapache-2.0
Downloads (HF)85
Last updated2023-10-07

Frequently asked questions about Wizard Orca 3B

How much VRAM does Wizard Orca 3B need?

About 5.4 GB at Q4_1 with an 8K context window. That is the 2.2 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 Wizard Orca 3B on an 8 GB GPU?

Yes, with Q5_1: the 2.6 GB file needs about 5.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Wizard Orca 3B GGUF?

It depends on the quant: Q4_0 is 2.0 GB, Q4_1 is 2.2 GB, Q5_0 is 2.4 GB, Q5_1 is 2.6 GB.

What context length does Wizard Orca 3B support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 2.7 GB at 8K and 0.7 GB at 2K.

Where can I download Wizard Orca 3B GGUF?

The files are on Hugging Face in the Aryanne/Wizard-Orca-3B-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 Wizard Orca 3B 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 Wizard Orca 3B on 8 GB VRAM?

Yes, the Q4_0 and Q4_1 quantizations fit within 8 GB VRAM, using approximately 5.2–5.4 GB at 8 k context.

Does Wizard Orca 3B support vision tasks?

No, the model has no vision capabilities.

What license applies to Wizard Orca 3B?

The model is released under the Apache‑2.0 license.

Similar models

Browse all →

More from Aryanne

All by Aryanne →

More Wizard models

All Wizard →

Other tiny models

All tiny models →