Gökdeniz Gülmez

My name got featured in one of Apples WWDC 2025 session videos 👀🍎 Crazy to think my work made it into a global Apple dev session. I’m proud!! Thanks @awnihannun @angeloskath @Apple

I joined Anthropic as a member of the technical staff. Excited to work on frontier modeling at a place with unwavering values and a generational mission.

@OpenAI @OpenAIDevs mlx directly supported, sweet!!!!!

Are you up for a challenge? openai.com/parameter-golf

@_albertgu mlx-lm pr is online github.com/ml-explore/mlx…

The newest model in the Mamba series is finally here 🐍 Hybrid models have become increasingly popular, raising the importance of designing the next generation of linear models. We've introduced several SSM-centric ideas to significantly increase Mamba-2's modeling capabilities without compromising on speed. The resulting Mamba-3 model has noticeable performance gains over the most popular previous linear models (such as Mamba-2 and Gated DeltaNet) at all sizes. This is the first Mamba that was student led: all credit to @aakash_lahoti @kevinyli_ @_berlinchen @caitWW9, and of course @tri_dao!

👀👀 github.com/ml-explore/mlx…

@0fir0z Thanks, I’ll add that🙏🏼🫶

If I can give you a piece of advice, put lore work and effort into your GitHub to demonstrate the importance value and great work you’ve done I know from personal interest the importance of your contribution, without ME PERSONALLY INTERESTED there is no way I could have understand this from your GitHub pages

Well I did it. Just activated GitHub Sponsors. ❤️ If my work on ML tooling, Apple Silicon training, or open-source AI projects (like mlx-lm-lora, or the JOSIE models) has helped you, consider supporting the development. Sponsorship helps me continue building and maintaining open tools for the ML community. github.com/sponsors/Goekd…

Fun conversation with @atiorh. We covered a lot of ground from Deep Speech to MLX and more:

@atiorh @awnihannun CAN'T WAITTTTTTTTT

Fun conversation with @awnihannun on MLX, on-device AI and more Pod coming in a few days

Finally 500 subs on @huggingface 🚀🎉🥳

An absolutely unforgettable afternoon in New York at Apple Grand Central!  Huge thank you to @AliciaKeys for helping us kick off the #Apple50 celebrations. What a way to mark 50 years, and we're just getting started!

@1littlecoder @tragichappy 🙏🏼🔥

@tragichappy @ActuallyIsaak It works with LMStudio - I tried it yesterday

Introducing the Josiefied-gabliterated Qwen3.5 0.8B model. Uncensored and (imo) with a better personality than the base model while making it smarter. the bigger ones are coming too. huggingface.co/Goekdeniz-Guel…

You always have such a impeccable style 🔥

So I have been recently, internally testing something 🤖

@HuggingModels More to come 😎

@ActuallyIsaak Awesome 🙌 thanks

@Prince_Canuma Will let you know ASAP

@ActuallyIsaak The QAT variant as well

@Prince_Canuma haven't tried it but will do that!!!!!

@ActuallyIsaak Could you gabliterate gemma3-12B-Instruct ? For LTX-2