Can RTX 3090 run Qwen3.6 35B-A3B?
Yes. Measured 146-153 tok/s generation (llama.cpp, llama-bench tg128 (quant per result); source).
Every measured result for Qwen3.6 35B-A3B on RTX 3090
| Build | Quant / setup | Engine | tok/s | |
|---|---|---|---|---|
| RTX 3090: 2026 models (llamabench community) | llama-bench tg128 (quant per result) | llama.cpp | 146-153 | source |
| Single RTX 3090: Qwen3.6 35B-A3B (Giles Thomas) | Q4 GGUF, all layers on GPU, ~90K ctx | llama.cpp CUDA | 139.6 | source |
| 4x RTX 3090 lab: Qwen3.6 on vLLM vs llama.cpp | IQ4_XS (1 GPU) | llama.cpp | 115-133 | source |
Memory: RTX 3090 has 24 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 · RTX 5090 · RTX Spark N1X
Other models measured on RTX 3090: DeepSeek R1 671B · Qwen3.6 27B · Qwen3.8 27B · gpt-oss 20B
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: RigBase may earn RunPod credit if you sign up. It never affects our data.
Referral link: RigBase may earn RunPod credit if you sign up. It never affects our data.
SPONSOR
Your brand here. One sponsor slot on this page, shown to people choosing AI hardware. Sponsor RigBase →
Your brand here. One sponsor slot on this page, shown to people choosing AI hardware. Sponsor RigBase →