the runtime protocol for intelligent systems
Joined July 2024
- Tweets54
- Following0
- Followers1.6K
- Likes455
TensorBlock retweeted
TensorBlock is building AI infrastructure from the ground up!
Dr. Mengshi Zhang and Dean Wang of @tensorblock_aoi joined @DavidThaDegen at @CES to talk about how TensorBlock got started, who it’s built for, and what they’re most excited about as the product comes to life.
0:28 - Introductions
0:58 - When TensorBlock started
1:34 - What is TensorBlock
2:00 - The core user
2:49 - When to get excited
3:17 - Their favorite parts of building
Watch the full video below!
Claude Opus 4.5 (@AnthropicAI ) is now supported on Forge.
Anthropic’s newest model brings stronger coding and agentic behavior with better SWE bench and tool-use performance.
On Forge, you can use Opus 4.5 through the same single API as every other supported provider.
Gemini 3.0 is now live on Forge.
You can call Google’s newest model through the same unified TensorBlock API you already use across providers.
One interface, many models. Switch providers without changing your application logic.
Try it here → forge.tensorblock.co
At KBW 🇰🇷, we joined @googlecloud, @eigencloud & @saharaai on the “Decentralizing Intelligence” panel at Hack Summit by @hack_vc.
Conversations highlighted the accelerating shift toward open AI and the growing demand for infrastructure to support agentic intelligence.
TensorBlock retweeted
The partnership with @tensorblock_aoi highlights how Walrus is becoming a foundation for scalable, AI-driven infrastructure.
We’re excited to work alongside @WalrusProtocol, the global data layer, to build the modular infrastructure for the next wave of AI-driven systems.
Together, we’re making intelligence open, composable, and ready to scale.
We’re excited to work alongside @WalrusProtocol, the global data layer, to build the modular infrastructure for the next wave of AI-driven systems.
Together, we’re making intelligence open, composable, and ready to scale.
TensorBlock retweeted
GLM-4.5 is now live on TensorBlock Forge, an open-source middleware service that simplifies AI model provider management.
Get your Z.ai API key here:
docs.z.ai/guides/overview/qu…
@tensorblock_aoi 🤝 @Zai_org
GLM-4.5, Z.ai’s most advanced LLM, is now live on TensorBlock Forge. Just connect your Z.ai API key to access it seamlessly through Forge’s unified interface.
This collaboration brings state-of-the-art AI capabilities to users—enabling smarter code generation, reasoning and stronger agentic functionalities.
Learn more and get started here: forge.tensorblock.co/
@tensorblock_aoi 🤝 @Zai_org
GLM-4.5, Z.ai’s most advanced LLM, is now live on TensorBlock Forge. Just connect your Z.ai API key to access it seamlessly through Forge’s unified interface.
This collaboration brings state-of-the-art AI capabilities to users—enabling smarter code generation, reasoning and stronger agentic functionalities.
Learn more and get started here: forge.tensorblock.co/
We're honored to be featured by @startuptofollow!
Thank you for the thoughtful interview and spotlight.
Check out the article here:
👉 startuptofollow.com/article/…
🔥 @claude_code Nerfed? We Got You Covered.
@AnthropicAI just dropped tighter weekly rate limits.
Auto-mode? 24/7 agents? Multi-threading? Say goodbye.
But with Forge, you stay unstoppable:
✅ Mix Claude Code with any model
✅ No code change
✅ Beat the cap. Stay in flow.
🛠 Try now: github.com/TensorBlock/claud…
Best performance. Full control. Let’s build. 💥
#vibecoders #claudecode #LLM #AItool #DevTools
🔥 Claude Code endpoint down? We don’t sweat it.
Forge lets you mix @ClaudeCode with any model — @OpenAI , @Google, @Alibaba_Qwen, @Kimi_Moonshot you name it.
No code change. Full flexibility.
💥 Our demo: Gemini 2.5 Flash as the fast-thinker
🚀 + Qwen3-Coder-480B as the heavy-hitter — but you pick your combo.
Best performance. Lower cost. Full control.
Claude who? 😉
Quickstart repo here 👉 github.com/TensorBlock/claud…
#ClaudeCode #Gemini #Qwen3 #LLM #AIInfra
Big milestone! We just hit 3 million downloads on @huggingface 🎉
With 4,823+ quantized models, each supporting 10+ precision formats, we're committed to making open-source AI more accessible and efficient for everyone.
And we’re far from done — we’ll keep building and contributing to the community.
Thank you for the love and support ❤️
🔗 huggingface.co/tensorblock
#AI #openLLM #quantization #HuggingFace #opensource #TensorBlock
TensorBlock retweeted
finally got some real sleep after 24h straight in the office launching Forge on @ProductHunt 😵💫
ft. my loyal teammate Pikachu & our office “bed” 🫠
hotfixing till 5am, answering Discord, support tickets, user calls, adhoc meetings… last time I felt this was @libra launch at midnight
somehow we made it: #1 product of the day 🥇
Let’s build!
🚀 Huge milestone!
Forge by TensorBlock just launched on @ProductHunt and ranked as the #1 Product of the Day, also featured as Best Product of the Day!
10K+ users
1B+ daily tokens served
500K+ daily requests
Thanks to everyone who supported us. We're just getting started.
🔗producthunt.com/products/ten… #AI #infrastructure #LLM
🚨 TensorBlock Forge is now live on Product Hunt! One API, all your AI models. OpenAI-compatible, privacy-first, and prod-ready. Help us hit the front page by leaving a comment and upvote!
producthunt.com/products/ten…
Thank you @AMD for an incredible event and all the exciting efforts behind it. It was a pleasure to share our insights on open-source AI and the emerging era of AI agents during the workshop time. We’ve always believed in AMD’s strengths, especially in the inference space #AdvancingAI
