What are the hardware requirements for VisionPsy Nano 460M Flash MLX?

VisionPsy Nano 460M Flash MLX requires approximately 1 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed VisionPsy Nano 460M Flash MLX and how large is it?

VisionPsy Nano 460M Flash MLX is developed by KaedeTai, a model with 460m parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate VisionPsy Nano 460M Flash MLX?

VisionPsy Nano 460M Flash MLX is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

VisionPsy Nano 460M Flash MLX by KaedeTai — VRAM 1GB

Name: VisionPsy Nano 460M Flash MLX
Author: KaedeTai

VisionPsy Nano 460M Flash MLX is an open-source language model by KaedeTai. Features: 460m LLM, VRAM: 1GB, License: apache-2.0.

Apple-silicon Base model:finetune:qvac/visio... Base model:qvac/visionpsy-nano... Conversational En Image-text-to-text Mlx Region:us Safetensors Siglip2 Smollm2 Vision Vision-language-model Visionpsy nano Vlm Zh

Model Card on HF 🤗: https://huggingface.co/KaedeTai/VisionPsy-Nano-460M-Flash-MLX

VisionPsy Nano 460M Flash MLX Parameters and Internals

LLM Name	VisionPsy Nano 460M Flash MLX
Repository 🤗	https://huggingface.co/KaedeTai/VisionPsy-Nano-460M-Flash-MLX
Base Model(s)	qvac/VisionPsy-Nano-460M-Flash qvac/VisionPsy-Nano-460M-Flash
Model Size	460m
Required VRAM	1 GB
Updated	2026-08-09
Maintainer	KaedeTai
Model Type	visionpsy_nano
Model Files	1.0 GB
Supported Languages	en zh
Model Architecture	VisionPsyNanoForConditionalGeneration
License	apache-2.0
Model Max Length	8192
Tokenizer Class	GPT2Tokenizer
Padding Token	<\|im_end\|>
Vocabulary Size	49152
Torch Data Type	bfloat16
Errors	replace

Rank the VisionPsy Nano 460M Flash MLX capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to VisionPsy Nano 460M Flash MLX

Best Alternatives	Context / RAM	Downloads	Likes
VisionPsy Nano 460M	0K / 2 GB	1391	17