LL

Llama 3.2 11B Vision Instruct

LlamaGGUF by pbatraUpdated 2025-01-23
Download on Hugging Face
Parameters9.78B
Context128K
Layers40
Architecturemllama
Smallest quant6.0 GB
Quick answer

Llama 3.2 11B Vision Instruct needs about 7.8 GB of memory at Q4_K_M (a 6.0 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 3 quants, from 6.0 GB (Q4_K_M) to 19.6 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

Llama 3.2 11B Vision Instruct – 9.78B parameters, vision and tool use

Llama 3.2 11B Vision Instruct is a 9.78B parameter model built on the mllama architecture. It supports vision input and tool invocation. The model is available in several GGUF quantizations.

Good at

  • Vision and image understanding
  • Tool usage and instruction following
  • Multimodal context handling

Limits

  • No explicit vision resolution limits listed
  • Requires 8k context for memory estimates
  • License is llama3.2

Best for

  • Image captioning tasks
  • Interactive tool‑based assistants
  • Multimodal content generation

Who it’s for. Developers building vision‑enabled assistants or tools that need instruction following. The model is suitable for applications that can handle the 8k context size and the specified memory requirements.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M6.0 GB 7.8 GB
Tight Get file →
Q8_010.4 GB 12.2 GB
Too big Get file →
—19.6 GB 21.4 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (5.96 GB file, 7.8 GB memory at 8k context). For 12 GB VRAM, Q8_0 (10.39 GB file, 12.2 GB memory). Larger models need more memory and are not recommended for low‑VRAM setups.

What GPU do you need for Llama 3.2 11B Vision Instruct?

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: no quant fits at an 8K context.
  • 8 GB VRAM: the best quant that fits is Q4_K_M (6.0 GB file, about 7.8 GB in use).
  • 12 GB VRAM: the best quant that fits is Q4_K_M (6.0 GB file, about 7.8 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (10.4 GB file, about 12.2 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (19.6 GB file, about 21.4 GB in use).

Which Llama 3.2 11B Vision Instruct quant should you choose?

Q4_K_M is the usual starting point for Llama 3.2 11B Vision Instruct: it balances file size and quality well. Here it is a 6.0 GB file.

The Q8_0 file is 10.4 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturemllama
Parameters9.78B
Layers40
Trained context131,072 tokens
KV cache (fp16)160 KB per token

Source

Quantized bypbatra
FamilyLlama
Licensellama3.2
Downloads (HF)824
Last updated2025-01-23

Frequently asked questions about Llama 3.2 11B Vision Instruct

How much VRAM does Llama 3.2 11B Vision Instruct need?

About 7.8 GB at Q4_K_M with an 8K context window. That is the 6.0 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 Llama 3.2 11B Vision Instruct on an 8 GB GPU?

Yes, with Q4_K_M: the 6.0 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Llama 3.2 11B Vision Instruct GGUF?

It depends on the quant: Q4_K_M is 6.0 GB, Q8_0 is 10.4 GB, file is 19.6 GB.

What context length does Llama 3.2 11B Vision Instruct support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.

Where can I download Llama 3.2 11B Vision Instruct GGUF?

The files are on Hugging Face in the pbatra/Llama-3.2-11B-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 11B 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.

Can I run Llama 3.2 11B Vision Instruct on 8 GB VRAM?

Yes, using the Q4_K_M quantization which requires approximately 7.8 GB memory at 8k context.

Does the model support vision input?

Yes, the model has detected vision ability and can process image data.

What quantization should I use for a 12 GB VRAM GPU?

Use the Q8_0 quantization; it needs about 12.2 GB memory at 8k context.

Other GGUFs of Llama-3.2-11B-Vision-Instruct

Similar models

Browse all →

More from pbatra

All by pbatra →

More Llama models

All Llama →

Other medium models

All medium models →