NA

VisionPsy Nano 460M GGUFs

NanovlmGGUF by qvacUpdated 2026-07-29
Download on Hugging Face
Parameters409M
Context8K
Layers32
Architecturellama
Smallest quant0.2 GB
Quick answer

VisionPsy Nano 460M GGUFs needs about 1.1 GB of memory at Q4_K_M (a 0.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 11 quants, from 0.2 GB (IQ3_XXS) to 1.6 GB.

Compact vision‑language model for edge devices

VisionPsy Nano 460M GGUFs is a 0.409 B parameter vision‑language model based on nanoVLM. It supports image‑to‑text inference with a 8192‑token context. The model is released under Apache‑2.0 and is available in multiple quantizations for llama.cpp.

Good at

  • Image‑to‑text generation
  • Multimodal inference on low‑resource hardware
  • Fast on‑device performance

Limits

  • Requires patched llama.cpp
  • Vision encoder fixed to Q8_0
  • No text‑only usage without image

Best for

  • Mobile photo captioning
  • Edge device visual question answering
  • Lightweight multimodal chatbots

Who it’s for. Developers building on‑device vision‑language applications who need a small footprint and fast inference. The model is suitable for phones, tablets, and embedded systems that can run llama.cpp.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ3_XXS0.2 GB 1.1 GB
Fits Get file →
IQ3_M0.3 GB 1.1 GB
Fits Get file →
IQ4_XS0.3 GB 1.1 GB
Fits Get file →
Q4_00.3 GB 1.1 GB
Fits Get file →
IQ4_NL0.3 GB 1.1 GB
Fits Get file →
Q4_K_M0.3 GB 1.1 GB
Fits Get file →
Q5_K_M0.3 GB 1.2 GB
Fits Get file →
Q5_K_M0.3 GB 1.2 GB
Fits Get file →
Q8_00.4 GB 1.3 GB
Fits Get file →
BF160.8 GB 1.7 GB
Fits Get file →
—1.6 GB 2.5 GB
Fits Get file →

For 8 GB VRAM, use IQ4_XS or Q4_K_M (≈0.25–0.30 GB, ~1.1 GB memory at 8k context). If 4 GB VRAM is available, IQ3_XXS or IQ3_M (≈0.24–0.25 GB, ~1.1 GB memory) are suitable. For the smallest memory footprint, IQ3_XXS is recommended.

What GPU do you need for VisionPsy Nano 460M GGUFs?

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 (1.6 GB file, about 2.5 GB in use).

Which VisionPsy Nano 460M GGUFs quant should you choose?

Q4_K_M is the usual starting point for VisionPsy Nano 460M GGUFs: it balances file size and quality well. Here it is a 0.3 GB file.

The Q8_0 file is 0.4 GB, about 1.4 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.

If memory is tight, the smallest file is IQ3_XXS at 0.2 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters409M
Layers32
Trained context8,192 tokens
KV cache (fp16)40 KB per token

Source

Quantized byqvac
FamilyNanovlm
Licenseapache-2.0
Downloads (HF)5,621
Last updated2026-07-29

Frequently asked questions about VisionPsy Nano 460M GGUFs

How much VRAM does VisionPsy Nano 460M GGUFs need?

About 1.1 GB at Q4_K_M with an 8K context window. That is the 0.3 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 VisionPsy Nano 460M GGUFs on an 8 GB GPU?

Yes, with the smaller files: the 1.6 GB file needs about 2.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of VisionPsy Nano 460M GGUFs GGUF?

It depends on the quant: IQ3_XXS is 0.2 GB, IQ3_M is 0.3 GB, IQ4_XS is 0.3 GB, Q4_0 is 0.3 GB, IQ4_NL is 0.3 GB, Q4_K_M is 0.3 GB and 5 more.

What context length does VisionPsy Nano 460M GGUFs support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 0.3 GB at 8K and 0.3 GB at 8K.

Where can I download VisionPsy Nano 460M GGUFs GGUF?

The files are on Hugging Face in the qvac/VisionPsy-Nano-460M-GGUFs repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does VisionPsy Nano 460M GGUFs 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 VisionPsy Nano 460M on 8 GB VRAM?

Yes, using IQ4_XS or Q4_K_M quantizations requires about 1.1 GB of VRAM at 8k context.

Does the model support text‑only inference?

No, the model requires the vision encoder and multimodal projector to function.

What license applies to the GGUF weights?

The weights are released under the Apache‑2.0 license.

Other GGUFs of nanoVLM-460M-8k

Similar models

Browse all →

More from qvac

All by qvac →

More Nanovlm models

All Nanovlm →

Other tiny models

All tiny models →