NA

VisionPsy Nano 460M Flash GGUFs

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

VisionPsy Nano 460M Flash 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.

VisionPsy Nano 460M Flash GGUFs – fast, on‑device vision‑language model

VisionPsy Nano 460M Flash is a 0.409 B llama‑based vision‑language model. It uses fewer visual tokens, delivering faster inference on mobile devices while maintaining high accuracy. The model is available in multiple GGUF quantizations for different memory budgets.

Good at

  • Fast image‑to‑text inference on phones
  • Low‑latency multimodal queries
  • Efficient use of VRAM

Limits

  • No vision support beyond image‑to‑text
  • Requires multimodal projector file
  • License is Apache‑2.0

Best for

  • Mobile image captioning
  • Quick visual question answering
  • Embedded vision‑language tasks

Who it’s for. Developers building lightweight vision‑language applications on edge devices. The model is suitable for projects that need fast inference and low memory usage while still handling image and text inputs.

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 IQ3_XXS or IQ3_M (≈1.1 GB memory at 8k context). For 4 GB VRAM, choose IQ4_XS or Q4_0 (≈1.1 GB). If you have 2 GB VRAM, the smallest is IQ3_XXS (≈1.1 GB).

What GPU do you need for VisionPsy Nano 460M Flash 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 Flash GGUFs quant should you choose?

Q4_K_M is the usual starting point for VisionPsy Nano 460M Flash 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)7,742
Last updated2026-07-29

Frequently asked questions about VisionPsy Nano 460M Flash GGUFs

How much VRAM does VisionPsy Nano 460M Flash 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 Flash 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 Flash 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 Flash 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 Flash GGUFs GGUF?

The files are on Hugging Face in the qvac/VisionPsy-Nano-460M-Flash-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 Flash 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 Flash on 4 GB VRAM?

Yes, using IQ4_XS or Q4_0 quantizations will fit within 4 GB VRAM with about 1.1 GB memory usage at 8k context.

Does the model support text‑only inference?

No, the model is vision‑language only and requires an image input to function.

What file do I need besides the GGUF?

You need the multimodal projector file (mmproj‑*.gguf) to process image inputs.

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 →