More
Submit build

Can RTX 3090 run Inkling 2 Mini?

Last updated:

Yes. Measured 73.5 tok/s generation (vLLM TP1 + Ampere overlay, 1 stream, W4A16 INT4; source).

Every measured result for Inkling 2 Mini on RTX 3090

BuildQuant / setupEnginetok/s
RTX 3090: Inkling 2 Mini W4A16 INT4 on vLLM TP1 + Ampere overlay, 73.5 tok/s median (Tech2wild)W4A16 INT4vLLM TP1 + Ampere overlay, 1 stream73.5source

Memory: RTX 3090 has 24 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 M3 Ultra · Apple M5 Ultra · DGX Spark (GB10) · RTX 4090

Other models measured on RTX 3090: DeepSeek R1 671B · Flint 40B-A2.5B · GLM 4.7 Flash · Gemma 4 31B · Nemotron 3.5 Bolt 74B-A9B · Nemotron 3.5 Lightning 30B-A3B · Qwen3.6 27B · Qwen3.6 35B-A3B · Qwen3.8 27B · Ripple 65B Preview · gpt-oss 120B · 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.