More
Submit build

Can RTX 5070 Ti run Raon-1 mini Preview?

Last updated:

Probably only partly: the weights are larger than its memory, so part of the model likely ran from system RAM. Measured 220 tok/s generation with part of the model offloaded to system RAM (ik_llama.cpp-raon fork (CUDA 12.8), IQ3_KS experts / IQ4_KS_R16 down (13.85 GB, 3.86 bpw), q8_0 KV; source).

Every measured result for Raon-1 mini Preview on RTX 5070 Ti

BuildQuant / setupEnginetok/s
RTX 5070 Ti 16 GB: KRAFTON Raon-1 mini preview (28.8B-A4.3B) IQ3_KS at ~220-230 tok/s on an ik_llama.cpp fork, 128K context fitsIQ3_KS experts / IQ4_KS_R16 down (13.85 GB, 3.86 bpw), q8_0 KVik_llama.cpp-raon fork (CUDA 12.8)220 CPU offloadsource
RTX 5070 Ti 16 GB: KRAFTON Raon-1 mini preview (28.8B-A4.3B) IQ3_KS at ~220-230 tok/s on an ik_llama.cpp fork, 128K context fitsIQ3_KS experts / IQ4_KS_R16 down (13.85 GB, 3.86 bpw), q8_0 KVik_llama.cpp-raon fork (CUDA 12.8)190 CPU offloadsource

Memory: RTX 5070 Ti has 16 GB. Raon-1 mini Preview weights are about 17.6 GB at Q4_K_M (28.8B params × 4.89 bits ÷ 8, before context/KV cache). 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 Raon-1 mini Preview: best home rig for Raon-1 mini Preview.

Raon-1 mini Preview on other hardware: RTX 5060 Ti 16GB · Radeon RX 7900 XTX

Other models measured on RTX 5070 Ti: Gemma 4 12B · Gemma 4 26B-A4B · Qwen3.5 9B · Qwen3.8 27B · gpt-oss 20B

Not enough VRAM? Rent before you buy. Run Raon-1 mini Preview 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.