New Apple #ML Research Highlight: "FastVLM: Efficient Vision Encoding for Vision Language Models" machinelearning.apple.com/research/fas...
FastVLM: Efficient Vision Encoding for Vision Language Models
Vision Language Models (VLMs) enable visual understanding alongside textual inputs. They are typically built by passing visual tokens from a…
machinelearning.apple.com
July 23, 2025 at 6:35 PM
New Apple #ML Research Highlight: "FastVLM: Efficient Vision Encoding for Vision Language Models" machinelearning.apple.com/research/fas...
enough to get the gears turning on local VLMs for iOS apps -- not nearly as good but also pretty amazing considering this runs on my phone github.com/apple/ml-fas...
GitHub - apple/ml-fastvlm: This repository contains the official implementation of "FastVLM: Efficient Vision Encoding for Vision Language Models" - CVPR 2025
This repository contains the official implementation of "FastVLM: Efficient Vision Encoding for Vision Language Models" - CVPR 2025 - apple/ml-fastvlm
github.com
January 6, 2026 at 12:56 AM
enough to get the gears turning on local VLMs for iOS apps -- not nearly as good but also pretty amazing considering this runs on my phone github.com/apple/ml-fas...
Apple just shook up the VLM scene — launching FastVLM and MobileCLIP2 as open-source alternatives to big-name commercial models! 🤗
Demo: huggingface.co/spaces/apple...
Demo: huggingface.co/spaces/apple...
September 1, 2025 at 4:28 PM
Apple just shook up the VLM scene — launching FastVLM and MobileCLIP2 as open-source alternatives to big-name commercial models! 🤗
Demo: huggingface.co/spaces/apple...
Demo: huggingface.co/spaces/apple...
Apple เปิดตัว FastVLM! โมเดล AI อ่านภาพเร็วขึ้น 85 เท่า
#ShoperGamer #Apple #Picture #FastVLM #Ai #ModelAi #Opensource #Feed
#ShoperGamer #Apple #Picture #FastVLM #Ai #ModelAi #Opensource #Feed
[Shoper Gamer] Apple เปิดตัว FastVLM! โมเดล AI อ่านภาพเร็วขึ้น 85 เท่า
โดย
โดย
www.blockdit.com
May 14, 2025 at 7:04 AM
Apple เปิดตัว FastVLM! โมเดล AI อ่านภาพเร็วขึ้น 85 เท่า
#ShoperGamer #Apple #Picture #FastVLM #Ai #ModelAi #Opensource #Feed
#ShoperGamer #Apple #Picture #FastVLM #Ai #ModelAi #Opensource #Feed
The inference code, model checkpoints, and an iOS/macOS demo app based on MLX are available here: github.com/apple/ml-fas...
GitHub - apple/ml-fastvlm: This repository contains the official implementation of "FastVLM: Efficient Vision Encoding for Vision Language Models" - CVPR 2025
This repository contains the official implementation of "FastVLM: Efficient Vision Encoding for Vision Language Models" - CVPR 2025 - apple/ml-fastvlm
github.com
July 23, 2025 at 6:35 PM
The inference code, model checkpoints, and an iOS/macOS demo app based on MLX are available here: github.com/apple/ml-fas...
Appleが精度と効率の両方を高水準でこなす独自の視覚言語モデル「FastVLM」を発表、オンデバイスでのリアルタイムビジュアルクエリ処理に最適
https://gigazine.net/news/20250724-apple-fastvlm-efficient-vision-language-models/
https://gigazine.net/news/20250724-apple-fastvlm-efficient-vision-language-models/
Appleが精度と効率の両方を高水準でこなす独自の視覚言語モデル「FastVLM」を発表、オンデバイスでのリアルタイムビジュアルクエリ処理に最適
Appleが独自の視覚言語モデル(VLM)となる「FastVLM」を発表しました。従来のVLMは精度が高くなると効率性が低下するという問題を抱えていたのですが、FastVLMは高い精度を保ちながら効率の面でも優れた性能を発揮しており、オンデバイスでのリアルタイムビジュアルクエリ処理に適したAIモデルになっているとのことです。
gigazine.net
July 24, 2025 at 5:42 AM
Appleが精度と効率の両方を高水準でこなす独自の視覚言語モデル「FastVLM」を発表、オンデバイスでのリアルタイムビジュアルクエリ処理に最適
https://gigazine.net/news/20250724-apple-fastvlm-efficient-vision-language-models/
https://gigazine.net/news/20250724-apple-fastvlm-efficient-vision-language-models/
Official Apple repository for FastVLM (CVPR 2025), an efficient vision–language stack built around the FastViTHD encoder to reduce visual tokens and latency.
Designed for on-device, real-time multimodal applications.
github.com/apple/ml-fas...
Designed for on-device, real-time multimodal applications.
github.com/apple/ml-fas...
GitHub - apple/ml-fastvlm: This repository contains the official implementation of "FastVLM: Efficient Vision Encoding for Vision Language Models" - CVPR 2025
This repository contains the official implementation of "FastVLM: Efficient Vision Encoding for Vision Language Models" - CVPR 2025 - apple/ml-fastvlm
github.com
October 22, 2025 at 9:47 AM
Official Apple repository for FastVLM (CVPR 2025), an efficient vision–language stack built around the FastViTHD encoder to reduce visual tokens and latency.
Designed for on-device, real-time multimodal applications.
github.com/apple/ml-fas...
Designed for on-device, real-time multimodal applications.
github.com/apple/ml-fas...
Apple has released FastVLM, an efficient Vision Language Model (VLM) designed for rapid high-resolution image processing. It can run directly on iPhones using MLX. This is highly beneficial for apps requiring real-time performance on the device.
May 12, 2025 at 4:25 PM
Apple has released FastVLM, an efficient Vision Language Model (VLM) designed for rapid high-resolution image processing. It can run directly on iPhones using MLX. This is highly beneficial for apps requiring real-time performance on the device.
You can try Apple’s lightning-fast video captioning model right from your browser
You can try Apple’s lightning-fast video captioning model right from your browser
A few months ago, Apple released FastVLM, a Visual Language Model (VLM) that offered near-instant high-resolution image processing. Now, you can take it for a spin, provided you have an Apple Silicon-powered Mac. Here’s how.
more…
9to5mac.com
September 1, 2025 at 9:50 PM
You can try Apple’s lightning-fast video captioning model right from your browser
- Demo iOS app: FastVLM also comes with an iOS demo app that showcases its performance on mobile devices.
github.com/apple/ml-fas...
github.com/apple/ml-fas...
ml-fastvlm/app at main · apple/ml-fastvlm
This repository contains the official implementation of "FastVLM: Efficient Vision Encoding for Vision Language Models" - CVPR 2025 - apple/ml-fastvlm
github.com
May 12, 2025 at 4:25 PM
- Demo iOS app: FastVLM also comes with an iOS demo app that showcases its performance on mobile devices.
github.com/apple/ml-fas...
github.com/apple/ml-fas...
Glad to see new efforts towards edge solution! https://github.com/apple/ml-fastvlm #computervision #generativeai #diffusion #VLM (via https://message.haoxiang.org)
GitHub - apple/ml-fastvlm: This repository contains the official implementation of "FastVLM: Efficient Vision Encoding for Vision Language Models" - CVPR 2025
This repository contains the official implementation of "FastVLM: Efficient Vision Encoding for Vision Language Models" - CVPR 2025 - apple/ml-fastvlm
github.com
July 25, 2025 at 3:16 PM
Glad to see new efforts towards edge solution! https://github.com/apple/ml-fastvlm #computervision #generativeai #diffusion #VLM (via https://message.haoxiang.org)
No more cloud dependence.
Everything happens locally in your browser, so your data stays private and you skip the hassle of installs or API calls.
This opens doors for accessibility, privacy-focused apps, and instant deployment for developers.
Github: github.com/apple/ml-fas...
Everything happens locally in your browser, so your data stays private and you skip the hassle of installs or API calls.
This opens doors for accessibility, privacy-focused apps, and instant deployment for developers.
Github: github.com/apple/ml-fas...
GitHub - apple/ml-fastvlm: This repository contains the official implementation of "FastVLM: Efficient Vision Encoding for Vision Language Models" - CVPR 2025
This repository contains the official implementation of "FastVLM: Efficient Vision Encoding for Vision Language Models" - CVPR 2025 - apple/ml-fastvlm
github.com
September 1, 2025 at 4:28 PM
No more cloud dependence.
Everything happens locally in your browser, so your data stays private and you skip the hassle of installs or API calls.
This opens doors for accessibility, privacy-focused apps, and instant deployment for developers.
Github: github.com/apple/ml-fas...
Everything happens locally in your browser, so your data stays private and you skip the hassle of installs or API calls.
This opens doors for accessibility, privacy-focused apps, and instant deployment for developers.
Github: github.com/apple/ml-fas...
애플이 공개한 FastVLM(Vision Language Model)은 온디바이스로 구동되는거 하며 속도며 모두 인상적이다.
github.com/apple/ml-fas...
github.com/apple/ml-fas...
May 13, 2025 at 1:06 PM
애플이 공개한 FastVLM(Vision Language Model)은 온디바이스로 구동되는거 하며 속도며 모두 인상적이다.
github.com/apple/ml-fas...
github.com/apple/ml-fas...
⚡🍎 #Apple launches #AI that is 85 TIMES faster than #ChatGPT Vision
#ArtificialIntelligence #YuriOntibon #FastVLM #OpenSource
#ArtificialIntelligence #YuriOntibon #FastVLM #OpenSource
September 11, 2025 at 2:05 PM
⚡🍎 #Apple launches #AI that is 85 TIMES faster than #ChatGPT Vision
#ArtificialIntelligence #YuriOntibon #FastVLM #OpenSource
#ArtificialIntelligence #YuriOntibon #FastVLM #OpenSource
Apple lanza FastVLM en Hugging Face: modelos de IA visual-lingüísticos (VLMs) en tiempo real, con tamaños de 0.5B, 1.5B y 7B parámetros, y soporte para WebGPU. ⚡️
85x más rápidos
3.4x más pequeños
7.9x más rápidos en la primera respuesta.
Todo directo en el navegador con transformers.js. 🤯
Demo
👇
85x más rápidos
3.4x más pequeños
7.9x más rápidos en la primera respuesta.
Todo directo en el navegador con transformers.js. 🤯
Demo
👇
FastVLM WebGPU - a Hugging Face Space by apple
Real-time video captioning powered by FastVLM
huggingface.co
August 29, 2025 at 10:42 PM
Apple lanza FastVLM en Hugging Face: modelos de IA visual-lingüísticos (VLMs) en tiempo real, con tamaños de 0.5B, 1.5B y 7B parámetros, y soporte para WebGPU. ⚡️
85x más rápidos
3.4x más pequeños
7.9x más rápidos en la primera respuesta.
Todo directo en el navegador con transformers.js. 🤯
Demo
👇
85x más rápidos
3.4x más pequeños
7.9x más rápidos en la primera respuesta.
Todo directo en el navegador con transformers.js. 🤯
Demo
👇
How fast is it? Here's the demo app running FastVLM 0.5B model on iPhone 16 Pro. Time to first token is shown on the screen, highlighting near real-time performance.
July 23, 2025 at 6:35 PM
How fast is it? Here's the demo app running FastVLM 0.5B model on iPhone 16 Pro. Time to first token is shown on the screen, highlighting near real-time performance.
Check out the code, models, and demo iOS/macOS app using MLX for our fast vision-language models, FastVLM:
github.com/apple/ml-fas...
Paper: "FastVLM: Efficient Vision Encoding for Vision Language Models", Anasosalu et al., CVPR 2025
arxiv.org/abs/2412.13303
#CVPR2025 #Apple #research
github.com/apple/ml-fas...
Paper: "FastVLM: Efficient Vision Encoding for Vision Language Models", Anasosalu et al., CVPR 2025
arxiv.org/abs/2412.13303
#CVPR2025 #Apple #research
May 7, 2025 at 12:20 PM
Check out the code, models, and demo iOS/macOS app using MLX for our fast vision-language models, FastVLM:
github.com/apple/ml-fas...
Paper: "FastVLM: Efficient Vision Encoding for Vision Language Models", Anasosalu et al., CVPR 2025
arxiv.org/abs/2412.13303
#CVPR2025 #Apple #research
github.com/apple/ml-fas...
Paper: "FastVLM: Efficient Vision Encoding for Vision Language Models", Anasosalu et al., CVPR 2025
arxiv.org/abs/2412.13303
#CVPR2025 #Apple #research
Today we have released the code and a demo iOS application for FastVLM - our extremely efficient and fast vision language model which runs on your device using MLX! You can check out the code and the app here: github.com/apple/ml-fas...
May 7, 2025 at 10:20 PM
Today we have released the code and a demo iOS application for FastVLM - our extremely efficient and fast vision language model which runs on your device using MLX! You can check out the code and the app here: github.com/apple/ml-fas...
https://github.com/apple/ml-fastvlm
FastVLM: Efficient Vision Encoding for Vision Language Models
#vlm
FastVLM: Efficient Vision Encoding for Vision Language Models
#vlm
GitHub - apple/ml-fastvlm: This repository contains the official implementation of "FastVLM: Efficient Vision Encoding for Vision Language Models" - CVPR 2025
This repository contains the official implementation of "FastVLM: Efficient Vision Encoding for Vision Language Models" - CVPR 2025 - apple/ml-fastvlm
github.com
September 5, 2025 at 6:42 AM
https://github.com/apple/ml-fastvlm
FastVLM: Efficient Vision Encoding for Vision Language Models
#vlm
FastVLM: Efficient Vision Encoding for Vision Language Models
#vlm
📰 🔴 SON DAKİKA: Apple’dan yapay zekada “görsel dil” devrimi: FastVLM
Kaynak: Donanım Haber
#haber #sondakika #gündem #türkiye #dünya
Kaynak: Donanım Haber
#haber #sondakika #gündem #türkiye #dünya
🔴 SON DAKİKA: Apple’dan yapay zekada “görsel dil” devrimi: FastVLM
Apple’dan yapay zekada “görsel dil” devrimi: FastVLM
www.donanimhaber.com
August 31, 2025 at 6:22 PM
📰 🔴 SON DAKİKA: Apple’dan yapay zekada “görsel dil” devrimi: FastVLM
Kaynak: Donanım Haber
#haber #sondakika #gündem #türkiye #dünya
Kaynak: Donanım Haber
#haber #sondakika #gündem #türkiye #dünya
⚡ Hackernews Top story: FastVLM: Dramatically Faster Vision Language Model from Apple
GitHub - apple/ml-fastvlm: This repository contains the official implementation of "FastVLM: Efficient Vision Encoding for Vision Language Models" - CVPR 2025
This repository contains the official implementation of "FastVLM: Efficient Vision Encoding for Vision Language Models" - CVPR 2025 - apple/ml-fastvlm
github.com
May 13, 2025 at 2:31 AM
⚡ Hackernews Top story: FastVLM: Dramatically Faster Vision Language Model from Apple
FastVLM: 視覚言語モデルのための効率的な視覚エンコーディング
FastVLM: Efficient vision encoding for vision language models
🔺 299
💬 22
🔗 HN Post | Article
FastVLM: Efficient vision encoding for vision language models
🔺 299
💬 22
🔗 HN Post | Article
GitHub - apple/ml-fastvlm: This repository contains the official implementation of "FastVLM: Efficient Vision Encoding for Vision Language Models" - CVPR 2025
This repository contains the official implementation of "FastVLM: Efficient Vision Encoding for Vision Language Models" - CVPR 2025 - apple/ml-fastvlm
github.com
May 13, 2025 at 1:43 PM
Apple práve predstavil AI modely FastVLM a MobileCLIP2, ktoré robia zázraky ✨
⚡ Beží 85× rýchlejšie
📱 Zaberá 3,4× menej miesta
🎥 Titulkuje videá v reálnom čase priamo na vašom iPhone, priamo v prehliadači, bez inštalácie! 🍏
🔒 Žiadne cloudy = viac súkromia
⏱️ Žiadne čakanie = všetko ihneď
1/2 #bp
⚡ Beží 85× rýchlejšie
📱 Zaberá 3,4× menej miesta
🎥 Titulkuje videá v reálnom čase priamo na vašom iPhone, priamo v prehliadači, bez inštalácie! 🍏
🔒 Žiadne cloudy = viac súkromia
⏱️ Žiadne čakanie = všetko ihneď
1/2 #bp
September 2, 2025 at 7:12 PM
Apple práve predstavil AI modely FastVLM a MobileCLIP2, ktoré robia zázraky ✨
⚡ Beží 85× rýchlejšie
📱 Zaberá 3,4× menej miesta
🎥 Titulkuje videá v reálnom čase priamo na vašom iPhone, priamo v prehliadači, bez inštalácie! 🍏
🔒 Žiadne cloudy = viac súkromia
⏱️ Žiadne čakanie = všetko ihneď
1/2 #bp
⚡ Beží 85× rýchlejšie
📱 Zaberá 3,4× menej miesta
🎥 Titulkuje videá v reálnom čase priamo na vašom iPhone, priamo v prehliadači, bez inštalácie! 🍏
🔒 Žiadne cloudy = viac súkromia
⏱️ Žiadne čakanie = všetko ihneď
1/2 #bp
Launch FastVLM (huggingface.co/spaces/apple...) freely available on Hugging Face and set the OBS virtual camera as input
FastVLM WebGPU - a Hugging Face Space by apple
Real-time video captioning powered by FastVLM
huggingface.co
September 2, 2025 at 2:29 PM
Launch FastVLM (huggingface.co/spaces/apple...) freely available on Hugging Face and set the OBS virtual camera as input