LL

Llama 3.2 90B Vision Instruct

LlamaGGUF by ThaurockUpdated 2026-11-04
Download on Hugging Face
Parameters926M
Context—
Layers—
Architecturemllama
Smallest quant2.0 GB
Quick answer

Llama 3.2 90B Vision Instruct needs about 108.3 GB of memory at Q8_0 (a 96.2 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 3 quants, from 2.0 GB (F16) to 177.4 GB (F16).

Llama 3.2 90B Vision Instruct is a 926M-parameter Llama model in GGUF format, quantized by Thaurock. The repository has 3 quant files, from 2.0 GB (F16) to 177.4 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F162.0 GB 2.7 GB
Fits Get file →
Q8_096.2 GB 108.3 GB
Too big Get file →
F16177.4 GB 199.2 GB
Too big Get file →

What GPU do you need for Llama 3.2 90B Vision Instruct?

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 F16 (2.0 GB file, about 2.7 GB in use).
  • 6 GB VRAM: the best quant that fits is F16 (2.0 GB file, about 2.7 GB in use).
  • 8 GB VRAM: the best quant that fits is F16 (2.0 GB file, about 2.7 GB in use).
  • 12 GB VRAM: the best quant that fits is F16 (2.0 GB file, about 2.7 GB in use).
  • 16 GB VRAM: the best quant that fits is F16 (2.0 GB file, about 2.7 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (2.0 GB file, about 2.7 GB in use).
  • 32 GB VRAM: the best quant that fits is F16 (2.0 GB file, about 2.7 GB in use).
  • 48 GB VRAM: the best quant that fits is F16 (2.0 GB file, about 2.7 GB in use).

Which Llama 3.2 90B Vision Instruct quant should you choose?

Q8_0 (96.2 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

If memory is tight, the smallest file is F16 at 2.0 GB, with the quality trade-offs that come with fewer bits. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturemllama
Parameters926M

Source

Quantized byThaurock
FamilyLlama
Licensellama3.2
Downloads (HF)273
Last updated2026-11-04

Frequently asked questions about Llama 3.2 90B Vision Instruct

How much VRAM does Llama 3.2 90B Vision Instruct need?

About 108.3 GB at Q8_0 with an 8K context window. That is the 96.2 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 Llama 3.2 90B Vision Instruct on an 8 GB GPU?

Yes, with F16: the 2.0 GB file needs about 2.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Llama 3.2 90B Vision Instruct GGUF?

It depends on the quant: F16 is 2.0 GB, Q8_0 is 96.2 GB, F16 is 177.4 GB.

Where can I download Llama 3.2 90B Vision Instruct GGUF?

The files are on Hugging Face in the Thaurock/Llama-3.2-90B-Vision-Instruct-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 Llama 3.2 90B Vision Instruct use?

Hugging Face lists the license as llama3.2. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Similar models

Browse all →

More from Thaurock

All by Thaurock →

More Llama models

All Llama →

Other tiny models

All tiny models →