Said | CeliaLabs

Custom AI automations and fine-tuning — for teams and solo operators. Runs on your hardware. Free recipes + tests posted here. DM "BUILD"

[Said | CeliaLabs @Celia_Labs]

You're probably losing hours every week to work a machine could do for you.
I build those machines — apps & automations that handle the repetitive stuff:
• Businesses: agents that qualify leads, answer support, kill data entry
• You personally: small tools that quietly run your day in the background

My edge: I can build them to run privately on your own hardware — your data never leaves the building.
That's CeliaLabs.
Got a repetitive task — at work or at home? Drop it below and I'll tell you if it's automatable 👇

[Said | CeliaLabs @Celia_Labs]

Qwen 3.8 Flash ...

[Said | CeliaLabs @Celia_Labs]

Just pulled the trigger on the new Mac Studio for local AI.
Can't wait to push Apple silicon and MLX to the limit.

#MLX #COREAI #Apple #LocalAI

[Said | CeliaLabs @Celia_Labs]

Every local AI lover right now…

The story isn’t over yet, check the replies for the rest 👇

[Said | CeliaLabs @Celia_Labs]

This is hilarious 😂😂
Finally someone explained the current AI Ecosystem

[Said | CeliaLabs @Celia_Labs]

@zebassembly Using everyday
Perfect for everyday needs
But Be careful it hallucinate a lot

[Said | CeliaLabs @Celia_Labs]

Everyone is arguing about which model to use.
Meanwhile the teams shipping working agents are spending their time on:
— tool interfaces the model can actually use
— what goes in the context window, and what doesn’t
— error handling and retries
— orchestration and task decomposition
The model is maybe 20% of the outcome. The harness is the rest.
(Until your task horizon gets long. Then the model becomes the ceiling again.)

[Said | CeliaLabs @Celia_Labs]

Open models closed 80% of the gap. I still pay for both.

I deploy local AI for myself and for clients. Privacy work, volume work, anything repetitive — that all runs local now, at zero marginal cost.

But I keep Claude Pro. Not for better answers — for fewer wasted passes on large codebases. Local models make me babysit context, and that babysitting is the real cost.

Gemini Pro I’d cancel. That’s a convenience tax on ecosystem lock-in, not a capability edge.
Buying back hours beats saving $20.

What’s still on your bill — and what’s keeping it there?

[DeepSeek @deepseek_ai]

DeepSeek-V4-Flash-Vision-Exp is now live on the DeepSeek API Platform! 🚀

🔹 This experimental multimodal model matches DeepSeek-V4-Flash on text capabilities—including agents, reasoning, and world knowledge.
🔹 On multimodal agent benchmarks, V4-Flash-Vision-Exp makes a major leap over V4-Flash, bringing multimodal agent performance close to Opus-4.8.

Try it with model='deepseek-v4-flash-vision-exp'. DeepSeek Harness 0.1.1 was released today with out-of-the-box support for the new model.

1/n

[Said | CeliaLabs @Celia_Labs]

@markproduct LC

[Said | CeliaLabs @Celia_Labs]

@aditikbuilds Lacal ai systems implementation

[Said | CeliaLabs @Celia_Labs]

DFlash 2 is the real deal.
Tested it on an M5 Pro MacBook Pro for coding workflows in OpenCode—easily outperforming both MTP and DSpark.

Game-changing acceleration for local models.
Thank you @zhijianliu_! 🔥

[Zhijian Liu @zhijianliu_]

DFlash 2 is here! Qwen3.8-27B at 70 tok/s on an M5 Max MacBook Pro.

⚡ Up to 4.6× the speed of autoregressive decoding, with the same output.

This is the next generation of DFlash, seeded at Z Lab and upgraded at Inco AI. Get one more accepted token on every pass, for free!

https://t.co/We0lwYPSBl

[Said | CeliaLabs @Celia_Labs]

Hey @Alibaba_Qwen, the chunky capybaras are cozy on the racks, but our edge devices are starving! 🦫⚡️

When can we get the official smol squad (0.8B, 2B, 4B, 9B)? Let the little guys run free on our laptops! 🚀💻 #Qwen #LocalAI

[Said | CeliaLabs @Celia_Labs]

I love #OpenSource 😍
Thank you, China. 🇨🇳❤️
谢谢中国 🇨🇳

@MiniMax_AI @deepseek_ai @Zai_org @Alibaba_Qwen @Kimi_Moonshot

[Said | CeliaLabs @Celia_Labs]

Been testing #Gemini 3.7 Flash recently
It’s the best overall: fastest, most efficient, model out there. ⚡️

[Said | CeliaLabs @Celia_Labs]

@minchoi @ClementDelangue Are these metrics tested and verified

[Wësche @WescheNex1q]

Qwen3.8-27B on Apple vs NVIDIA

M4 Max (MLX 4-bit):
29.5 tok/s decode · 248 tok/s prefill · 8.6K prompt = ~35s wait

DGX Spark (vLLM NVFP4 + native MTP):
24 tok/s on code, 17 on prose · ~2,000 tok/s prefill · 8.6K prompt = 4.3s

Same Q4 file on the same engine: Mac decodes 2× faster (21 vs 11.5)
that's the memory bus talking. But the Spark ingests context 8× faster, and it's the only one that can use the model's built-in MTP head, no Mac runtime supports it yet.

Mac wins the conversation. Spark wins the moment you paste a document. Same brain, two bodies — buy for your workload.

[Said | CeliaLabs @Celia_Labs]

This is a Game changer IMHO.

#opensource

[DeepSeek @deepseek_ai]

🧩 DeepSeek Harness v0.1 is now available in Developer Preview!

🔹 We’re opening it up to developers building agent harnesses worldwide and open-sourcing the codebase in MIT license.
🔹 Powered by the Cordis meta-framework, DeepSeek Harness is an agent harness built around one core idea: Everything is a plugin. Models, tools, skills, sessions, sandboxes, filesystems, loops, orchestration, and UI are ALL implemented as plugins, and can be mixed, matched, replaced, and extended.

Try it now!
https://t.co/2YWSvJHhKA

[Said | CeliaLabs @Celia_Labs]

@koraykv 3.6 Flash is already good for everyday tasks.
We're still waiting the 3.5 Pro