enzo (@enzostvs) header
enzo (@enzostvs) profile picture

frontend engineer @huggingface 🤗 owner of https://teapawt.net/t.co/qUkTYAiUep and https://teapawt.net/t.co/LAhgXUiUuc

qc
Joined August 2022
Photo by enzo (@enzostvs)Photo by enzo (@enzostvs)Photo by enzo (@enzostvs)Photo by enzo (@enzostvs)Photo by enzo (@enzostvs)Photo by enzo (@enzostvs)Photo by enzo (@enzostvs)Photo by enzo (@enzostvs)Photo by enzo (@enzostvs)Photo by enzo (@enzostvs)
OpenRouter Broadcast sends every trace wherever you want. Now that includes Hugging Face Buckets 🪣 With one setting in @OpenRouter and you can send them to a bucket you own with zero code changes. → fine-tune or distill on your own agent runs → run online evals on real traffic → find which calls burn your budget Setup: openrouter.ai/docs/guides/fe…
2
4
14
837
ok I had to try: same demo, open model. DiffusionGemma 26B-A4B + vLLM PR #57250 (structured reads) on my own custom endpoint. Using Matt's exact same sentences 👀 Mostly the same answers, a few fun misses (it thinks Luigi is blue 😂)
does Jev understand colour? incredible model, very cheap and fast. definitely feels like a leap forward for creating new UX/UI paradigms on top of modern language models.
11
11
1
79
9,381
enzo retweeted
Les étudiants ici, je sais que pour bcp c'est compliqué financièrement d’acheter toutes les fournitures, mettez en réponse les liens de ce dont vous avez besoin je vais essayer de trouver une marque avec qui faire une opé et jvous reverserai l'intégralité en fournitures scolaires
555
4,326
84
25,885
1,828,272
LTX-2 trainer is a huge deal. I tried it to add water to the podracers scene using their demo water-sim fine-tune (it's a fine-tune whose only goal is to add water :D) I think we're going to see film productions that don't use general models. They'll train their own fine-tunes, built for exactly what they need and consistent between shots for long content.
52
93
17
863
95,378
GLM-5.2 is available on Hugging Face 🔥 It's an important day for open source AI: opus-class frontier intelligence, 1M context, agentic-first by design. --> The future of AI and humanity is open
Introducing GLM-5.2: Frontier Intelligence, Open Weights - Significant improvements in coding and agentic tasks - Strong long-horizon capabilities with a 1M context window - Two levels of reasoning effort: GLM-5.2 (max) pushes the limits, while GLM-5.2 (high) strikes a strong balance between performance and token efficiency - MIT-licensed open weights - Same API pricing as GLM-5.1 Tech Blog: z.ai/blog/glm-5.2 Weights: huggingface.co/zai-org/GLM-5… API: docs.z.ai/guides/llm/glm-5.2 Coding Plan: z.ai/subscribe Chat: chat.z.ai
8
11
117
6,259
Created gaussian splats website for famous Paris monuments. Connected my claude code to HF Spaces API that let it call gaussian splatting tool (TripoSplat by VAST AI). I will explain 🧵
4
6
49
4,927
🐳 is back!
🚀 DeepSeek-V4 Preview is officially live & open-sourced! Welcome to the era of cost-effective 1M context length. 🔹 DeepSeek-V4-Pro: 1.6T total / 49B active params. Performance rivaling the world's top closed-source models. 🔹 DeepSeek-V4-Flash: 284B total / 13B active params. Your fast, efficient, and economical choice. Try it now at chat.deepseek.com via Expert Mode / Instant Mode. API is updated & available today! 📄 Tech Report: huggingface.co/deepseek-ai/D… 🤗 Open Weights: huggingface.co/collections/d… 1/n
25
85
6
1,717
77,229
enzo retweeted
me and @claudeai
216
4,395
350
33,725
1,702,813
the shift is real: in 2026 invest on AI builders 🤗
12
31
2
533
46,985
je testais le service messagerie.numerique.gouv.fr, je vois que la création d'alias ne marche pas, et je trouve ça dans les logs merci pour tout les devs
21
165
17
2,691
140,056
you can use gmod to verify your age by the way
Discord announces that users will need to verify their age from early March onwards in-order-to access age restricted content. All accounts will be set to a “teen-by-default” experience until otherwise verified as an adult. (discord.com/press-releases/d…)
428
11,796
370
186,506
8,104,087
New on HF Hub: you can now see check your hardware compatibility with MLX models directly on the model pages 🥳
10
15
3
120
18,398
we shipped a new thing like it / hate it?
28
6
7
194
47,901
Why is a 100% open source chatbot faster than ChatGPT "Instant"? 👀
102
25
10
802
234,854
GradientGen, my open-source and 100% free gradient creation tool, is now available! I'm excited to see what you'll do with it, have fun! :)
GradientGen V1 is out! - 8 gradient modes - 20+ variables - Export up to 8000 pixels - Unlimited use Enjoy ! noegarsoux.github.io/Gradien…🔷
15
15
3
445
24,570
🤗 @huggingface's most impactful contributors you should follow for the month of October is out! 🚀🚀 huggingface.co/spaces/TCTF/T… 🏛️ Top 10 Model likes: @TheBlokeAI, #mradermacher, @bartowski1182, #lllyasviel, #hexgrad, #nitrosocke, @kijaidesign, @haruu1367, @prompthero, #WarriorMama777 📊 Top 10 Dataset likes: @fkadev, @teknium, @maximelabonne, #gsdf, #Nerfgun3, @imhaotian, @OilandLuca, @logcong0120, @jon_durbin, #anon8231489123 🚀 Top 10 Space likes: @fffiloni, @multimodalart, @enzostvs, @flngr, @_akhaliq, @kingnish24, @xenovacom, @angrypenguinpng, @gokayfem, @yvrjsharma 🤗 Top 10 Profile followers: @TheBlokeAI, @lvminzhang, @mervenoyann, @bartowski1182, @_akhaliq, @ylecun, @fffiloni, @xenovacom, @maximelabonne, @Teknium Congarts to all users 🔥🔥
6
10
32
12,910
New: Qwen-Image-2509-MultipleAngles. Very solid model and probably a lot of creative use cases to find with it. ⬇️ Free demo available on Hugging Face
31
90
15
1,180
748,977
The main breakthrough of GPT-5 was to route your messages between a couple of different models to give you the best, cheapest & fastest answer possible. This is cool but imagine if you could do this not only for a couple of models but hundreds of them, big and small, fast and slow, in any language or specialized for any task - all at inference time. This is what we're introducing with HuggingChat Omni, powered by over 100 open-source models including gpt-oss, deepseek, qwen, kimi, smolLM, gemma, aya and many more already! And this is just the beginning as there are over 2 millions open models not only for text but image, audio, video, biology, chemistry, time-series and more on @huggingface!
115
153
50
1,637
269,059
Introducing: HuggingChat Omni 💫 Select the best model for every prompt automatically 🚀 - Automatic model selection for your queries - 115 models available across 15 providers Available now all Hugging Face users. 100% open source.
41
104
25
511
72,553
Anyway if any Vercel employees are weirdly looking elsewhere right now, I'm looking for a Senior Software Engineer for my team at Netlify. 💅
102
855
39
13,631
517,236