LL

SpaceLLaVA

LLaVAGGUF by remyxaiUpdated 2025-04-20
Download on Hugging Face
Parameters13B
Context4K
Layers40
Architecturellama
Smallest quant7.4 GB
Quick answer

SpaceLLaVA needs about 14.6 GB of memory at Q4_0 (a 7.4 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 2 quants, from 7.4 GB (Q4_0) to 26.0 GB (F16).

SpaceLLaVA: 13B multimodal model for spatial reasoning

SpaceLLaVA is a vision‑language model based on llava‑v1.5‑13b. It is fine‑tuned with LoRA to enhance spatial reasoning using synthetic VQA data. The model supports image and text inputs and is licensed under Apache‑2.0.

Good at

  • Spatial relationship queries
  • Image‑based VQA
  • Multimodal instruction following

Limits

  • No vision support beyond RGB images
  • Limited to 4096 context tokens
  • Requires GPU for efficient inference

Best for

  • Research on spatial reasoning
  • Developing spatial VQA applications
  • Testing multimodal instruction models

Who it’s for. Researchers and hobbyists working on computer vision, natural language processing, and multimodal AI. The model is suitable for academic projects and prototype development.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_07.4 GB 11.2 GB
Too big Get file →
F1626.0 GB 29.9 GB
Too big Get file →

For 8 GB VRAM use the Q4_0 quantized file (7.37 GB, ~14.6 GB memory at 8k context). For higher precision and more VRAM use the F16 file (26.03 GB, ~33.2 GB memory at 8k context).

What GPU do you need for SpaceLLaVA?

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: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: the best quant that fits is Q4_0 (7.4 GB file, about 14.6 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_0 (7.4 GB file, about 14.6 GB in use).
  • 32 GB VRAM: the best quant that fits is Q4_0 (7.4 GB file, about 14.6 GB in use).
  • 48 GB VRAM: the best quant that fits is F16 (26.0 GB file, about 33.2 GB in use).

Which SpaceLLaVA quant should you choose?

Q4_0 (7.4 GB) is the middle option in this repository. 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
Parameters13B
Layers40
Trained context4,096 tokens
KV cache (fp16)800 KB per token

Source

Quantized byremyxai
FamilyLLaVA
Licenseapache-2.0
Downloads (HF)837
Last updated2025-04-20

Frequently asked questions about SpaceLLaVA

How much VRAM does SpaceLLaVA need?

About 14.6 GB at Q4_0 with an 8K context window. That is the 7.4 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 SpaceLLaVA on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 14.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of SpaceLLaVA GGUF?

It depends on the quant: Q4_0 is 7.4 GB, F16 is 26.0 GB.

What context length does SpaceLLaVA support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 6.7 GB at 8K and 3.4 GB at 4K.

Where can I download SpaceLLaVA GGUF?

The files are on Hugging Face in the remyxai/SpaceLLaVA repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does SpaceLLaVA 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 SpaceLLaVA on 8 GB VRAM?

Yes, the Q4_0 quantized file is 7.37 GB and requires about 14.6 GB memory at 8k context, which fits in 8 GB VRAM with swapping.

Does SpaceLLaVA support video input?

No, the model only accepts RGB image inputs and text prompts.

Similar models

Browse all →

More from remyxai

All by remyxai →

More LLaVA models

All LLaVA →

Other medium models

All medium models →