Can 2x RTX 5090 run Qwen3.6 35B-A3B?
Last updated:
Yes. Measured 274 tok/s generation (llama.cpp b11910 (CUDA 13.4), one card (FE A), Q4_K_M (20.4 GB); source).
Every measured result for Qwen3.6 35B-A3B on 2x RTX 5090
| Build | Quant / setup | Engine | tok/s | |
|---|---|---|---|---|
| 2x RTX 5090 FE (Ryzen 9 9950X, llama.cpp b11910): Qwen3.6 35B-A3B Q4_K_M at 274 tok/s, Qwen3.8 27B Q4_K_M at 73 (llama-bench, one card) | Q4_K_M (20.4 GB) | llama.cpp b11910 (CUDA 13.4), one card (FE A) | 274 | source |
Memory: 2x RTX 5090 has 64 GB. Qwen3.6 35B-A3B weights are about 21.7 GB at Q4_K_M (35.51B 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 Qwen3.6 35B-A3B: best home rig for Qwen3.6 35B-A3B.
Qwen3.6 35B-A3B on other hardware: 2x RTX 3090 · Apple M5 Ultra · DGX Spark (GB10) · Intel Arc Pro B70 · RTX 3090 · RTX 4090 · RTX 5080 · RTX 5090 · RTX Spark N1X · Radeon AI Pro R9700 · Radeon RX 7900 XTX · Strix Halo (Radeon 8060S)
Other models measured on 2x RTX 5090: Qwen3.8 27B
Not enough VRAM? Rent before you buy. Run Qwen3.6 35B-A3B 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.