RTX 3090: 2026 models (llamabench community)
| GPU(s) | RTX 3090 Amazon · eBay (used) · Newegg |
|---|---|
| VRAM / unified memory (GB) | 24 |
| CPU | |
| Motherboard | |
| RAM | |
| PSU | |
| Other | |
| Reported total cost | |
| Power |
Measured speed (generation tokens/sec)
| Model | Quant | Engine | tok/s |
|---|---|---|---|
| Qwen3.6 35B-A3B | llama-bench tg128 (quant per result) | llama.cpp | 146-153 |
| Qwen3.6 27B | llama-bench tg128 (quant per result) | llama.cpp | 40.2 |
| Qwen3.8 27B | llama-bench tg128 (quant per result) | llama.cpp | 38.2-71.6 |
Community llama-bench results aggregated by llamabench.ai (decode tok/s, short context). Only runs without speculative decoding listed unless noted. Open the source for exact quant and llama.cpp version. Qwen3.6 27B and Qwen3.8 27B rows include runs with MTP/draft speculative decoding.
Source: https://llamabench.ai/browse/rtx3090
Blank fields = not stated in the source. We never estimate build data; GPU street prices above are separately sourced and dated.
Rent before you buy: try this model on a cloud GPU for a few dollars first: RunPod
Quick answers: Can RTX 3090 run Qwen3.6 27B? · Can RTX 3090 run Qwen3.6 35B-A3B? · Can RTX 3090 run Qwen3.8 27B?