Can Radeon RX 7900 XTX run Raon-1 mini Preview?
Last updated:
Yes. Measured 75.46 tok/s generation (llama.cpp KRAFTON fork + PR #1 kernel profile (ROCm 7.2.1), IQ4_XS GGUF; source).
Every measured result for Raon-1 mini Preview on Radeon RX 7900 XTX
| Build | Quant / setup | Engine | tok/s | |
|---|---|---|---|---|
| RX 7900 XTX (ROCm 7.2.1): KRAFTON Raon-1 mini preview IQ4_XS at 64.6 tok/s, 75.5 with opt-in fused kernels + backend sampler reuse | IQ4_XS GGUF | llama.cpp KRAFTON fork + PR #1 kernel profile (ROCm 7.2.1) | 75.46 | source |
| RX 7900 XTX (ROCm 7.2.1): KRAFTON Raon-1 mini preview IQ4_XS at 64.6 tok/s, 75.5 with opt-in fused kernels + backend sampler reuse | IQ4_XS GGUF | llama.cpp KRAFTON fork + PR #1 kernel profile (ROCm 7.2.1) | 64.57 | source |
Memory: Radeon RX 7900 XTX has 24 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 · RTX 5070 Ti
Other models measured on Radeon RX 7900 XTX: Qwen3.6 35B-A3B
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.
Referral link: if you sign up with Google and add $10, Runpod gives you and RigBase bonus credit (terms). It never affects our data.