NVIDIA GeForce RTX 3090 Ti
24 GB · 1,008 GB/s · 450 W
Prices
Every retailer we track in the US, cheapest first. Buy links may earn us a commission.
| Retailer | Condition | Price | Stock | Checked | Buy |
|---|---|---|---|---|---|
| AmazonEVGA GeForce RTX 3090 Ti FTW3 Black Gaming | refurbished | $1,900 | In stock | 17 min ago | Buy |
| AmazonEVGA GeForce RTX 3090 Ti FTW3 Ultra Gaming | refurbished | $2,050 | In stock | 17 min ago | Buy |
| AmazonASUS TUF Gaming NVIDIA GeForce RTX 3090 Ti OC Edition Graphics Card | New | $2,060 | In stock | 17 min ago | Buy |
| AmazonEVGA GeForce RTX 3090 Ti FTW3 Ultra Gaming | New | $2,080 | In stock | 17 min ago | Buy |
| AmazonNvidia RTX 3090 TI Founders Edition | refurbished | $2,100 | In stock | 17 min ago | Buy |
| AmazonGIGABYTE GIGABYTE GeForce RTX 3090 Ti Gaming OC 24G Graphics Card | refurbished | $2,190 | In stock | 17 min ago | Buy |
| AmazonMSI GeForce RTX 3090 Ti SUPRIM X 24G Gaming Graphics Card | refurbished | $2,200 | In stock | 17 min ago | Buy |
| AmazonZOTAC Gaming GeForce RTX 3090 Ti AMP Extreme Holo 24GB GDDR6X 384-bit 21 Gbps… | refurbished | $2,200 | In stock | 17 min ago | Buy |
| AmazonZOTAC Gaming GeForce RTX 3090 Ti AMP Extreme Holo 24GB GDDR6X 384-bit 21 Gbps… | New | $2,349 | In stock | 17 min ago | Buy |
| AmazonEVGA GeForce RTX 3090 Ti FTW3 GAMING | New | $2,400 | In stock | 17 min ago | Buy |
| AmazonNvidia GeForce RTX 3090 Ti Founders Edition | New | $2,450 | In stock | 17 min ago | Buy |
| AmazonGigabyte GeForce RTX 3090 Ti Gaming OC 24G Graphics Card | New | $2,465 | In stock | 17 min ago | Buy |
| AmazonGigabyte AORUS GeForce RTX 3090Ti Xtreme WATERFORCE 24G Graphics Card | New | $2,495 | In stock | 17 min ago | Buy |
| AmazonEVGA GeForce RTX 3090 Ti FTW3 BLACK GAMING | New | $2,499 | In stock | 17 min ago | Buy |
| AmazonASUS ROG Strix LC NVIDIA GeForce RTX 3090 Ti OC Edition Gaming Graphics Card | New | $2,665 | In stock | 17 min ago | Buy |
Price history
Lowest price shown each day over the last 90 days.
Not enough price history yet.
What two of them run
Every model in the catalogue, with the best quant for this hardware. Estimates, not measurements.
| Model | Quant | Fits | Memory | Max context | Decode @8k | Prefill | Good for |
|---|---|---|---|---|---|---|---|
| Qwen 3.8 27B Alibaba Qwen | Q8_0 | fits | 28.8 GB | 256k | 21tok/sest. | 630 tok/s | chat, long documents |
| Qwen 3.5 122B-A10B Alibaba Qwen | UD-Q2_K_XL | fits | 40.4 GB | 224k256k with q8 cache | 101tok/sest. | 1666 tok/s | chat, coding, agents, long documents |
| Qwen 3.6 27B Alibaba Qwen | Q8_0 | fits | 28.4 GB | 256k | 21tok/sest. | 630 tok/s | chat, coding, long documents |
| Qwen3 Coder Next Alibaba Qwen | Q4_K_M | fits | 46.6 GB | 14k23k with q8 cache | 142tok/sest. | 4208 tok/s | chat, coding, agents, long documents |
| Gemma 4 31B | Q8_0 | fits | 32.9 GB | 172k256k with q8 cache | 18tok/sest. | 549 tok/s | chat |
| Mistral Small 4 119B Mistral AI | UD-Q2_K_XL | fits | 38.8 GB | 296k471k with q8 cache | 146tok/sest. | 2177 tok/s | chat, coding, agents, long documents |
| Qwen 3.6 35B-A3B Alibaba Qwen | Q8_0 | fits | 35.7 GB | 256k | 113tok/sest. | 5396 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 27B Alibaba Qwen | Q8_0 | fits | 28.4 GB | 256k | 21tok/sest. | 630 tok/s | chat, coding, long documents |
| Gemma 4 26B-A4B | Q8_0 | fits | 26.5 GB | 256k | 83tok/sest. | 4112 tok/s | chat, coding, agents, long documents |
| GLM 4.5 Air Z.ai | Q2_K | fits | 44.8 GB | 18k34k with q8 cache | 44tok/sest. | 831 tok/s | chat |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q4_K_M | fits | 46.6 GB | 15k24k with q8 cache | 182tok/sest. | 5290 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q8_0 | fits | 35.7 GB | 256k | 113tok/sest. | 5396 tok/s | chat, coding, agents, long documents |
| GLM 4.7 Flash Z.ai | Q8_0 | fits | 31.2 GB | 198k | 66tok/sest. | 3020 tok/s | chat, coding, agents, long documents |
| Devstral Small 2 24B Mistral AI | Q8_0 | fits | 25.7 GB | 137k251k with q8 cache | 24tok/sest. | 710 tok/s | chat, coding |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | UD-Q6_K_XL | fits | 33.8 GB | 256k | 110tok/sest. | 5623 tok/s | chat, coding, agents, long documents |
| Kimi Linear 48B-A3B Moonshot AI | Q6_K | fits | 38.9 GB | 588k802k with q8 cache | 145tok/sest. | 5129 tok/s | chat, coding, long documents |
| gpt-oss 20B OpenAI | MXFP4 | fits | 12.6 GB | 128k | 142tok/sest. | 3906 tok/s | chat, coding, agents, long documents |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q8_0 | fits | 32.1 GB | 155k256k with q8 cache | 94tok/sest. | 3904 tok/s | chat, coding, agents, long documents |
| Qwen3 32B Alibaba Qwen | Q8_0 | fits | 35.6 GB | 40k | 17tok/sest. | 486 tok/s | chat |
| Gemma 4 12B | Q8_0 | fits | 13.4 GB | 256k | 48tok/sest. | 1433 tok/s | chat, coding, long documents |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 10.3 GB | 256k | 64tok/sest. | 1814 tok/s | chat, coding, long documents |
| Mistral Small 3.2 24B Mistral AI | Q8_0 | fits | 25.7 GB | 128k | 24tok/sest. | 710 tok/s | chat, coding |
| Gemma 3 27B | Q8_0 | fits | 28.9 GB | 128k | 21tok/sest. | 638 tok/s | chat, long documents |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q8_0 | fits | 35.6 GB | 51k95k with q8 cache | 17tok/sest. | 508 tok/s | chat |
| Llama 3.3 70B Meta | Q4_K_M | fits | 43.2 GB | 19k35k with q8 cache | 14tok/sest. | 237 tok/s | – |
| Ministral 3 14B Mistral AI | Q8_0 | fits | 15.8 GB | 199k256k with q8 cache | 40tok/sest. | 1178 tok/s | chat, coding, long documents |
| Qwen3 14B Alibaba Qwen | Q8_0 | fits | 17.0 GB | 40k | 37tok/sest. | 1095 tok/s | chat, coding, long documents |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q8_0 | fits | 10.4 GB | 128k | 63tok/sest. | 1915 tok/s | chat, coding, long documents |
| Qwen3 8B Alibaba Qwen | Q8_0 | fits | 10.4 GB | 40k | 63tok/sest. | 1915 tok/s | chat, coding, long documents |
| Phi-4 14B Microsoft | Q8_0 | fits | 17.2 GB | 16k | 36tok/sest. | 1102 tok/s | chat, coding |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 5.6 GB | 256k | 130tok/sest. | 3652 tok/s | chat, coding, long documents |
| Ministral 3 8B Mistral AI | Q8_0 | fits | 10.6 GB | 256k | 62tok/sest. | 1790 tok/s | chat, coding, long documents |
| Granite 4.2 8B IBM | Q8_0 | fits | 11.1 GB | 128k | 59tok/sest. | 1776 tok/s | chat, coding, agents, long documents |
| Gemma 4 E4B | Q8_0 | fits | 9.0 GB | 128k | 74tok/sest. | 2199 tok/s | chat, coding, long documents |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 9.9 GB | 125k | 256tok/sest. | 12833 tok/s | chat, coding, long documents |
| Llama 3.1 8B Meta | Q6_K | fits | 8.3 GB | 128k | 82tok/sest. | 1977 tok/s | chat, coding, long documents |
| Nemotron 3 Super 120B-A12B NVIDIA | UD-Q2_K_XL | offload | 52.3 GB | – | 32tok/sest. | 1373 tok/s | chat, coding, long documents |
| gpt-oss 120B OpenAI | MXFP4 | offload | 60.5 GB | – | 32tok/sest. | 2434 tok/s | chat, coding |
| DeepSeek V4 Flash DeepSeek | UD-Q2_K_XL | won't run | 92.0 GB | – | – | – | – |
| GLM 5.3 Flash Z.ai | UD-Q2_K_XL | won't run | 102.6 GB | – | – | – | – |
| Qwen 3.8 Flash Next Alibaba Qwen | UD-Q2_K_XL | won't run | 74.9 GB | – | – | – | – |
| MiniMax M2.7 MiniMax | UD-Q2_K_XL | won't run | 73.2 GB | – | – | – | – |
Specifications
From the manufacturer's published specifications; sources are linked where we have them.
- GPU
- GeForce RTX 3090 Ti
- Memory
- 24 GB GDDR6X
- Memory bus
- 384-bit
- Memory bandwidth
- 1,008 GB/s
- FP16 compute
- 80 TFLOPS
- Software
- CUDA
- Board power
- 450 W
- PCIe generation
- Gen 4
- PCIe lanes
- x16