Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

Moondream 2B running on an iPhone

vikhyatk's profile picture

vik

20,935 subscribers

33,412 görüntüleme • 1 yıl önce •via X (Twitter)

EğitimBilim & Teknoloji
LIVE

Anya Rossi• Live Now

Private livecam show

11 Yorum

vik profil fotoğrafı
vik1 yıl önce

will be releasing ported weights + inference code soon, stay tuned!

baki profil fotoğrafı
baki1 yıl önce

why is there a Minecraft video on right lol, are we on TikTok?

vik profil fotoğrafı
vik1 yıl önce

my apologies, will do subway surfer next time

Charan profil fotoğrafı
Charan1 yıl önce

I thought moondream was some model which generates game regions. I was waiting for it to pop on the Minecraft UI.

vik profil fotoğrafı
vik1 yıl önce

sorry... just wanted to give people something to look at while the spinner was spinning

ΜΛΛNΙ profil fotoğrafı
ΜΛΛNΙ1 yıl önce

wat?! this is almost temporally perfect how did you do it before deepmind?! what's your food and sleep routine?! and how can I get this good?!

vik profil fotoğrafı
vik1 yıl önce

they have a model running on mobile but it sucks food/sleep -- i don't do either

Andrew Ngmi profil fotoğrafı
Andrew Ngmi1 yıl önce

Is there a MLX port?

vik profil fotoğrafı
vik1 yıl önce

using coreml here

Maziyar PANAHI profil fotoğrafı
Maziyar PANAHI1 yıl önce

Pretty cool! Would love to learn how to fine-tune this for an on-device ocr!

vik profil fotoğrafı
vik1 yıl önce

working on an OCR-focused finetune so hopefully you won't have to do it yourself! what languages are you interested in?

Benzer Videolar

Twilight Princess running native on an iPhone 17 at 120 fps
2:21

Twilight Princess running native on an iPhone 17 at 120 fps

Pheenoh

342,598 görüntüleme • 2 ay önce

Quantized Gemma 2B runs pretty fast on my iPhone 15 pro in MLX Swift. code & docs: Comparable to GPT 3.5 turbo and Mixtral 8x7B in LMSYS Org benchmarks but runs efficiently on an iPhone. Pretty wild.
0:25

Quantized Gemma 2B runs pretty fast on my iPhone 15 pro in MLX Swift. code & docs: Comparable to GPT 3.5 turbo and Mixtral 8x7B in LMSYS Org benchmarks but runs efficiently on an iPhone. Pretty wild.

Awni Hannun

79,702 görüntüleme • 1 yıl önce

The new Qwen 3.5 by Qwen running on-device on iPhone 17 Pro. Qwen 3.5 beats models 4 times its size, has strong visual understanding, and can toggle reasoning on or off. The 2B 6-bit model here is running with MLX optimized for Apple Silicon.
0:25

The new Qwen 3.5 by Qwen running on-device on iPhone 17 Pro. Qwen 3.5 beats models 4 times its size, has strong visual understanding, and can toggle reasoning on or off. The 2B 6-bit model here is running with MLX optimized for Apple Silicon.

Adrien Grondin

3,553,119 görüntüleme • 3 ay önce

Releasing moondream-zig! It is a fast, implementation of moondream2 inference on the CPU written from-scratch in Zig :) moondream-zig provides 1.5-2x faster inference compared to huggingface on the same device. moondream vik
1:21

Releasing moondream-zig! It is a fast, implementation of moondream2 inference on the CPU written from-scratch in Zig :) moondream-zig provides 1.5-2x faster inference compared to huggingface on the same device. moondream vik

snow

29,245 görüntüleme • 1 yıl önce

New Moondream 2B release! ✨ New features: - Long-form captioning - Open vocab tagging - Better counting, object detection, text understanding - Faster HF transformers inference
0:26

New Moondream 2B release! ✨ New features: - Long-form captioning - Open vocab tagging - Better counting, object detection, text understanding - Faster HF transformers inference

vik

51,735 görüntüleme • 1 yıl önce

Excited to release a preview of Moondream 3. A 9B param, 2B active MoE vision language model that makes no compromises; offering state-of-the-art visual reasoning while still retaining an efficient and deployment-friendly form factor.
0:48

Excited to release a preview of Moondream 3. A 9B param, 2B active MoE vision language model that makes no compromises; offering state-of-the-art visual reasoning while still retaining an efficient and deployment-friendly form factor.

vik

227,429 görüntüleme • 9 ay önce

Running Qwen3 8B thinking on an iPhone Air with MLX. The model is quantized to 4-bit and runs pretty well.
0:45

Running Qwen3 8B thinking on an iPhone Air with MLX. The model is quantized to 4-bit and runs pretty well.

Awni Hannun

215,529 görüntüleme • 9 ay önce

Device Speed & Lag Example of the lag seen on an IPhone 15 PM running iOS 26 when configuring Lock Screen #iOS26
1:06

Device Speed & Lag Example of the lag seen on an IPhone 15 PM running iOS 26 when configuring Lock Screen #iOS26

Is iOS Stable?

13,460 görüntüleme • 1 yıl önce

Qwen3.5-2B vs Qwen3.5-9B rap battle running locally on 2 foidable phones
1:16

Qwen3.5-2B vs Qwen3.5-9B rap battle running locally on 2 foidable phones

alexine 🏴‍☠️

134,226 görüntüleme • 3 ay önce

Alibaba’s Qwen 3.5 is now running fully on-device on the iPhone 17 Pro. It outperforms models 4x its size, delivers strong visual understanding, and lets you switch reasoning on or off. This demo uses the 2B 6-bit version, optimized with MLX for Apple Silicon.
0:24

Alibaba’s Qwen 3.5 is now running fully on-device on the iPhone 17 Pro. It outperforms models 4x its size, delivers strong visual understanding, and lets you switch reasoning on or off. This demo uses the 2B 6-bit version, optimized with MLX for Apple Silicon.

Hugging Models

202,723 görüntüleme • 3 ay önce

"It's an iPhone -4!" 🤣 Roy upgrading his phone might be football’s longest-running saga!📱
0:54

"It's an iPhone -4!" 🤣 Roy upgrading his phone might be football’s longest-running saga!📱

The Overlap

232,460 görüntüleme • 29 gün önce

⚡️New "Thinking" UI with DeepSeek R1 Distilled models, running completely locally on iPhone
0:58

⚡️New "Thinking" UI with DeepSeek R1 Distilled models, running completely locally on iPhone

Private LLM

188,633 görüntüleme • 1 yıl önce

At 0x41con, I talked about how a newer version of Trigon was developed for A7 - A9 and A11 devices. I demoed the following untethered iOS 14 jailbreak, which is 100% reliable on all devices thanks to Trigon - the following video shows it running on an iPhone 6S and an iPhone 7.
0:50

At 0x41con, I talked about how a newer version of Trigon was developed for A7 - A9 and A11 devices. I demoed the following untethered iOS 14 jailbreak, which is 100% reliable on all devices thanks to Trigon - the following video shows it running on an iPhone 6S and an iPhone 7.

Alfie

58,666 görüntüleme • 1 yıl önce

Running 400B model on iPhone! 0.6 t/s Credit Dan Woods @alexintosh Daniel Isaac Anemll
3:51

Running 400B model on iPhone! 0.6 t/s Credit Dan Woods @alexintosh Daniel Isaac Anemll

Anemll

291,615 görüntüleme • 3 ay önce

This is using an iPhone 14 basic, but it can be used on an iPhone 12-15 sc ig/angel_sensia
0:32

This is using an iPhone 14 basic, but it can be used on an iPhone 12-15 sc ig/angel_sensia

Mutia

139,653 görüntüleme • 8 ay önce

iPhone running at 1 Hz be like:
1:29

iPhone running at 1 Hz be like:

Noah Cat

194,329 görüntüleme • 1 yıl önce

🇵🇸🇮🇱 Doctor’s in Gaza are having to operate under the flashlight of an iPhone due to power running low.
0:44

🇵🇸🇮🇱 Doctor’s in Gaza are having to operate under the flashlight of an iPhone due to power running low.

Censored Men

5,628,561 görüntüleme • 2 yıl önce

Updated my HF Space for vibe testing smol VLMs on object detection, visual grounding, keypoint detection & counting! 👓 🆕Compare Qwen2.5 VL 3B vs Moondream 2B side-by-side with annotated images & text outputs. Try examples or test your own images! 🏃👇
0:45

Updated my HF Space for vibe testing smol VLMs on object detection, visual grounding, keypoint detection & counting! 👓 🆕Compare Qwen2.5 VL 3B vs Moondream 2B side-by-side with annotated images & text outputs. Try examples or test your own images! 🏃👇

Sergio Paniego

15,717 görüntüleme • 11 ay önce

Ronaldo’s thoughts on buying his son an iPhone.
0:44

Ronaldo’s thoughts on buying his son an iPhone.

Deepak Prabhu

480,220 görüntüleme • 1 yıl önce

Announcing moondream 0.5B, the world's smallest vision language model.
0:36

Announcing moondream 0.5B, the world's smallest vision language model.

vik

58,888 görüntüleme • 1 yıl önce