Mobius Labs

Multimodal AI for the world's scale.
Proponents of Open Source and Open Intelligence.
for some of our recent work.

[Mobius Labs @Mobius_Labs]

@Dropbox is acquiring our IP, and the Mobius core tech team is joining them. A huge milestone for us!

https://t.co/pglCNRmneK

[mobicham @mobicham]

https://t.co/orcApi6B7J
You can now easily load various pre-quantized models (block FP8, NVFP4, AWQ/GPTQ/HQQ, certain GGUFs) via a vLLM plugin! You can also run on-the-fly quant as well, easy to use: 1 or 2 flags to enable!

[mobicham @mobicham]

Skimming through the PolarQuant paper by Google and found HQQ is still alive 👀

[mobicham @mobicham]

Babe, wake up, new GemLite update.
Up to 1.7x+ faster FP8 block quantization on the RTX PRO 6000 end-2-end in vLLM!

[Josh Clemm @joshclemm]

Open sourcing something fun from @Dropbox: Witchcraft.

It's a local search engine built in Rust with no API keys or vector DB required.

Think: ColBERT / late interaction style retrieval, but packaged to run locally (perfect for coding agents).

Let's dive in👇

[Pamela Fox @pamelafox]

This was a great talk at DSpy meetup about how Dropbox optimized their search relevance judge:
https://t.co/Wx7hx2pobY
Also available in blog post form:
https://t.co/V2nI5PSA2G

DSpy both improved structural conformance of SLM output (valid JSON) and agreement with humans (NMSE).

[Omar Khattab @lateinteraction]

Wow! Quite a detailed blog from @Dropbox on how they optimize Dropbox Dash relevance judge with @DSPyOSS.

Shout out to the Dropbox Dash team Eric Wang, Dmitriy Meyerzon, and @joshclemm !

[mobicham @mobicham]

New blogpost 🫡!
https://t.co/xhtjPfcLBJ

[mobicham @mobicham]

hmm isn't it obvious this would work better than QAT? I’ve been doing this already for HQQ+, the DeepSeek re-distill work, and FP4 weight quant quality recovery. More comments below 🧵

[Mobius Labs @Mobius_Labs]

If you’re at @EurIPSConf this week and looking for your next ML role, ping us. Few of us from @Dropbox including @mobicham @appughar will be there Happy to chat about roles in multimodal, search, and video-AI.

[Mobius Labs @Mobius_Labs]

Looking for people with experience in : Building and scaling multimodal ML systems, Retrieval, ranking, and creative search problems, Turning prototypes into polished products
🌍 Remote (Germany or Denmark)
Apply here: https://t.co/utBstvNyM4 (Please use the link, not DMs!)

[Mobius Labs @Mobius_Labs]

Looking for people with experience in : Building and scaling multimodal ML systems, Retrieval, ranking, and creative search problems, Turning prototypes into polished products
🌍 Remote (Germany or Denmark)
Apply here: https://t.co/utBstvNyM4 (Please use the link, not DMs!)

[Mobius Labs @Mobius_Labs]

We are looking for a Machine Learning Engineer (IC3) to join our Multimedia AI team at Dropbox!

You’ll work on the ML behind Dropbox Dash, building real multimodal search experiences across images, video, and text — and ship things that millions of people actually use.

[Mobius Labs @Mobius_Labs]

@Dropbox is acquiring our IP, and the Mobius core tech team is joining them. A huge milestone for us!

https://t.co/pglCNRmneK

[Drew Houston @drewhouston]

And for my fellow nerds: with Dash, we're obsessed with depth of context, not just breadth. Dash isn't just calling APIs and doing naive keyword search. We build a full semantic index of all your content that is natively multimodal: not just documents but images, videos, everything.

This is the only way to build true understanding and close the context gap to make AI actually useful at work.

[Josh Clemm @joshclemm]

The best AI apps need the right context and @Dropbox Dash is built to provide it.

Thrilled to welcome the incredible tech and talent from @Mobius_Labs to the team.

Multimodal AI will make the Dash context platform even stronger 💪

[Mobius Labs @Mobius_Labs]

@Dropbox Keep supporting us, keep an eye on what's next, give Dropbox Dash a spin… or come join us to take this search + AI revolution to the next level. https://t.co/VDPhpDTYlI

[Mobius Labs @Mobius_Labs]

@Dropbox is acquiring our IP, and the Mobius core tech team is joining them. A huge milestone for us!

https://t.co/pglCNRmneK

[Mobius Labs @Mobius_Labs]

@Dropbox Now, we get to take that spirit to @Dropbox scale — building GenAI-native apps that reimagine how people work.

[mobicham @mobicham]

Looking forward to the @GPU_MODE hackathon later this Friday! Your boi will be there and happy to assist 🫡

[mobicham @mobicham]

Kinda disappointed by Qwen3-VL's decoder perf with vLLM so far. Can squeeze better perf via GemLite instead of DeepGEMM but the numbers still seem suspiciously low