More
Submit build

Can Apple M3 Ultra run Inkling 2 Mini?

Last updated:

Yes. Measured 40.3 tok/s generation (oMLX v0.8.1, MTP off, oMLX Inkling-2-Mini (as labelled); source).

Every measured result for Inkling 2 Mini on Apple M3 Ultra

BuildQuant / setupEnginetok/s
Mac Studio M3 Ultra 512GB (oMLX, MTP off): Inkling 2 Mini at 40.3 tok/s at 1k context, 28.4 tok/s at 195koMLX Inkling-2-Mini (as labelled)oMLX v0.8.1, MTP off40.3source
Mac Studio M3 Ultra 512GB (oMLX, MTP off): Inkling 2 Mini at 40.3 tok/s at 1k context, 28.4 tok/s at 195koMLX Inkling-2-Mini (as labelled)oMLX v0.8.1, MTP off39.5source
Mac Studio M3 Ultra 512GB (oMLX, MTP off): Inkling 2 Mini at 40.3 tok/s at 1k context, 28.4 tok/s at 195koMLX Inkling-2-Mini (as labelled)oMLX v0.8.1, MTP off39.4source
Mac Studio M3 Ultra 512GB (oMLX, MTP off): Inkling 2 Mini at 40.3 tok/s at 1k context, 28.4 tok/s at 195koMLX Inkling-2-Mini (as labelled)oMLX v0.8.1, MTP off38.7source
Mac Studio M3 Ultra 512GB (oMLX, MTP off): Inkling 2 Mini at 40.3 tok/s at 1k context, 28.4 tok/s at 195koMLX Inkling-2-Mini (as labelled)oMLX v0.8.1, MTP off37.3source
Mac Studio M3 Ultra 512GB (oMLX, MTP off): Inkling 2 Mini at 40.3 tok/s at 1k context, 28.4 tok/s at 195koMLX Inkling-2-Mini (as labelled)oMLX v0.8.1, MTP off34.4source
Mac Studio M3 Ultra 512GB (oMLX, MTP off): Inkling 2 Mini at 40.3 tok/s at 1k context, 28.4 tok/s at 195koMLX Inkling-2-Mini (as labelled)oMLX v0.8.1, MTP off30.9source
Mac Studio M3 Ultra 512GB (oMLX, MTP off): Inkling 2 Mini at 40.3 tok/s at 1k context, 28.4 tok/s at 195koMLX Inkling-2-Mini (as labelled)oMLX v0.8.1, MTP off28.4source

Memory: Apple M3 Ultra has 512 GB. Inkling 2 Mini weights are about 20 GB in its native format (Thinking Machines Lab model card: 26.4B total / 3.4B active looped MoE (middle layers run 3 times, ~5.4B effective active), text + image in, up to 1M context, Apache 2.0, released 20 Nov 2026; one ~20 GB NVFP4/MXFP8 checkpoint). Arithmetic, not a measurement; long contexts need more. Check other quants in the VRAM calculator.

Speeds are decode (generation) tokens/sec as reported by each source; quant, engine and context differ, so small gaps are noise.

All measured speeds for Inkling 2 Mini: best home rig for Inkling 2 Mini.

Inkling 2 Mini on other hardware: 2x RTX 3090 · Apple M5 Ultra · DGX Spark (GB10) · RTX 3090 · RTX 4090

Other models measured on Apple M3 Ultra: DeepSeek R1 671B · DeepSeek V4.1 Flash · MiniMax M3.1 Flash · Mistral Medium 3.5 128B · Muse Spark Open 816B-A42B · Qwen3.8 27B · Ripple 65B Preview · gpt-oss 20B

Not enough VRAM? Rent before you buy. Run Inkling 2 Mini on a bigger GPU on a rented 24–96 GB cloud GPU by the hour and see the real speed before spending €1,000+. Try it on Runpod
Referral link: if you sign up with Google and add $10, Runpod gives you and RigBase bonus credit (terms). It never affects our data.