Darkbloom

@darkbloomai

Open Inference Network of Idle Macs. Public Alpha. Live on OpenRouter. An @EigenLabs Project.

San Francisco, CA

darkbloom.ai

Replies Reposts Media

Pinned
Darkbloom
@darkbloomai
Sep 18
NEW: Bonsai 2 is LIVE on Darkbloom PrismML compressed Qwen3.8 27B to 8.5 GB and kept 98.2% of its benchmark scores. A full 27B reasoning model that fits on a phone. On Darkbloom, it runs from a browser tab. First 250 users get 100 million free tokens. console.darkbloom.dev/chat
Gajesh
@gajesh
Sep 18
01:20
Darkbloom is the first model provider to support Ternary Bonsai 2 27B -- concentrated intelligence that fits on your phone. Try it now: console.darkbloom.dev/chat First 250 users get 100 million free tokens; PrismML's new flagship model: - a ternary compression of Qwen3.8 27B at
4
Darkbloom
@darkbloomai
Sep 18
Bonsai 2 coming to Darkbloom A 27B model in 5.9 GB. Most Macs already on the network can serve it, no new hardware needed. Stay tuned.
Kydo
@0xkydo
Sep 18
Today's my birthday, and I could not have asked for a better gift. Bonsai 2 fits on most phones shipping today (anything >8GB). And it outperforms Opus 4.6 and 5.6 Luna -- on tasks that would have sounded absurd to attempt anywhere two years ago. I try to be disciplined about
8
Darkbloom
@darkbloomai
Aug 27
Matthew Berman just took Darkbloom for a spin. "Just imagine we have a million of these nodes set up. That is major inference power that anybody can tap into at a fraction of the price of going to an OpenAI or an Anthropic. And it's completely distributed. It is completely built
Gajesh
@gajesh
Aug 27
Yayy!! Thank you, @MatthewBerman for covering Darkbloom. Really great to see this; your optimistic energy is infectious and feels great to see more believers in our mission to keep accelerating the frontier of open compute networks. Darkbloom is one shot at making anyone
1
Darkbloom
@darkbloomai
Aug 27
Gemma 4 26B A4B is the most served model on Darkbloom right now. You serve compute on Darkbloom. Then you rally in MLX.fast to make compute faster. Let's turn MLX.fast into the open R&D arm for Darkbloom. LIVE on @yukonresearch:
Kydo
@0xkydo
Aug 27
MLX.fast turns one month old tomorrow 🎊🥳🎆 As an early celebration, we're kicking off our Gemma 4 challenge today. Gemma 4 runs on Darkbloom today (six billion tokens served yesterday). Any speedup we find here shows up as extra throughput on machines that are
2
Darkbloom
@darkbloomai
Aug 21
Update: Darkbloom is now a paid provider on @OpenRouter. We got 250 Macs online right now, in apartments and offices, serving production traffic on hardware that was idle before it joined the network. Total tokens served: 4.5 Billion. Operators earn $120 to $200 a month per
Gajesh
@gajesh
Aug 21
Darkbloom is back in action; Yesterday, we went from free tier to paid tier on OpenRouter. We have fulfilled on track close at 4.5B tokens served and $102K ARR. We are open network of Mac machines (250 online right now). On average, people are earning $120-200 per month per
40