Qwen3.6 27B landed yesterday, so I ran it on 4 setups side-by-side to see how they stack up:
🔴 RTX 4090 — 45.59 tok/s, TTFT 525ms
🟢 RTX 5090 — 51.83 tok/s, TTFT 752ms
⚫️ M2 Ultra — 22.30 tok/s, TTFT 216ms
🟣 DGX Spark — 11.08 tok/s, TTFT 319ms
This is a standard test: no tuning, just the out-of-the-box experience.
For the NVIDIA cards I used llama.cpp with Unsloth's UD-Q4_K_XL quant. For the M2 Ultra I used MLX with Unsloth's UD-MLX-4bit quant, since MLX is the native path on Apple Silicon.
Please consider this as the baseline, you can definitely squeeze more out of every one of these with fine-tuned settings.
Wake the world's sleeping compute.
Look at the Mac nearest to you. What's it doing?
Probably nothing.
There are 100M+ Macs with Apple Silicon out there. Apple quietly made them *really* good at inference. A $3k Mac runs a 60B model at 30 watts.
Most sit idle most of the day.
Meanwhile every AI API call passes through three layers of margin before reaching the hardware. We call this the Inference Tax.
We got curious: what happens if you connect idle Macs directly to inference demand?
This is Darkbloom. Private inference network for idle Macs.
darkbloom [dot] dev -- paper + code open.
Reply for invite + free credits ↓
@wealthy_barber@benjaminfelix Not even close. If you bought a home in the GTA in 2005 you be a millionaire today. If you invested the same down payment of $40k you’d have $269k…. Sure thing. How many rentals do you have?…
Congratulations to Donald J. Trump on his election as the 47th President of the United States.
The U.S. is Canada’s best friend and biggest trading partner, and I will work with the President to benefit both countries.
My mission: save our jobs.
The U.S. has already taken half a trillion dollars of investment and jobs from Canada under 9 years of Trudeau, and our people cannot afford homes and food. Yesterday’s result confirms we must cancel Trudeau’s plan to quadruple the carbon tax and hike other taxes, which would push hundreds of thousands more jobs south where President Trump will be cutting taxes even further.
We must axe taxes. Bring home our paycheques. Save our jobs. Stand up for Canada.
@AmexCanada Thanks @AmexCanada for the prompt reply. I am travelling with family (8 members), would they be able to join me me through the priority security lane? Also is there any way to receive the QR code in advance?
@spencmcgrath Hi Spencer, thank you for reaching out. Access to the Priority Security Lane for select Amex cards at Toronto Pearson Airport has changed. Eligible Cardmembers can visit the new Amex Kiosk to receive single-use QR codes for the Priority Security eGates in Terminals 1 & 3. (1/2)