LL

TinyLLaVA iOS clip base patch32

LLaVAGGUF by MasakiKUpdated 2025-04-15
Download on Hugging Face
Parameters1.1B
Context2K
Layers22
Architecturellama
Smallest quant0.7 GB
Quick answer

TinyLLaVA iOS clip base patch32 needs about 1.4 GB of memory at Q4_K (a 0.7 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 0.7 GB (Q4_K) to 2.2 GB.

TinyLLaVA iOS clip base patch32 is a 1.1B-parameter LLaVA model in GGUF format, quantized by MasakiK. Its trained context length is 2K tokens. The repository has 4 quant files, from 0.7 GB (Q4_K) to 2.2 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K0.7 GB 1.2 GB
Fits Get file →
Q4_K0.7 GB 1.2 GB
Fits Get file →
—2.2 GB 2.7 GB
Fits Get file →
—2.2 GB 2.7 GB
Fits Get file →

What GPU do you need for TinyLLaVA iOS clip base patch32?

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 (2.2 GB file, about 2.9 GB in use).

Which TinyLLaVA iOS clip base patch32 quant should you choose?

Q4_K (0.7 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_K at 0.7 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
Parameters1.1B
Layers22
Trained context2,048 tokens
KV cache (fp16)22 KB per token

Source

Quantized byMasakiK
FamilyLLaVA
Downloads (HF)11
Last updated2025-04-15

Frequently asked questions about TinyLLaVA iOS clip base patch32

How much VRAM does TinyLLaVA iOS clip base patch32 need?

About 1.4 GB at Q4_K with an 8K context window. That is the 0.7 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 TinyLLaVA iOS clip base patch32 on an 8 GB GPU?

Yes, with the smaller files: the 2.2 GB file needs about 2.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of TinyLLaVA iOS clip base patch32 GGUF?

It depends on the quant: Q4_K is 0.7 GB, Q4_K is 0.7 GB, file is 2.2 GB, file is 2.2 GB.

What context length does TinyLLaVA iOS clip base patch32 support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.0 GB at 2K.

Where can I download TinyLLaVA iOS clip base patch32 GGUF?

The files are on Hugging Face in the MasakiK/TinyLLaVA-iOS-clip-base-patch32 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from MasakiK

All by MasakiK →

More LLaVA models

All LLaVA →

Other tiny models

All tiny models →