RTX 3090 (llm-speed signed runs, Oct 2026): gpt-oss 20B 207 tok/s, Qwen3.6 27B 43 tok/s
| GPU(s) | RTX 3090 Amazon · eBay (used) · Newegg |
|---|---|
| VRAM / unified memory (GB) | 24 |
| CPU | AMD EPYC 7282 (GLM run: Threadripper PRO 5975WX) Amazon · eBay (used) · Newegg |
| Motherboard | |
| RAM | |
| PSU | |
| Other | Server hosts; llm-speed suite-v1 chat-short workload (128-token prompt, 256 tokens out, batch 1) |
| Reported total cost | |
| Power |
Measured speed (generation tokens/sec)
📏 How measured: reported by the original source; RigBase re-checked the numbers at that source
| Model | Quant | Engine | tok/s | Details |
|---|---|---|---|---|
| gpt-oss 20B | reported as Q4_K_M | llama.cpp 0.7.0-dev | 207.2 | |
| Qwen3.6 27B | Q4_K_M | llama.cpp 0.7.0-dev | 42.7 | |
| GLM 4.7 Flash | Q4_K_M (Threadripper PRO host) | Ollama 0.31.1 | 134.6 |
Signed community runs on llm-speed.com, 16-17 Oct 2026. Decode tok/s from the chat-short workload; chat-long (4K prompt): 199.8 (gpt-oss 20B), 42.3 (Qwen3.6 27B), 116.1 (GLM 4.7 Flash).
Source: https://llm-speed.com/r/r_nakw1nq6clw
https://llm-speed.com/r/r_qm1xyvjmx_r
https://llm-speed.com/r/r_kalwcyab-86
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 (referral link; sign up with Google to get the new-user bonus)
Quick answers: Can RTX 3090 run GLM 4.7 Flash? · Can RTX 3090 run Qwen3.6 27B? · Can RTX 3090 run gpt-oss 20B?