NVIDIA GeForce RTX 3090
24 GB · 936 GB/s · 350 W
In short
The NVIDIA GeForce RTX 3090 has 24 GB of GDDR6X memory with 936 GB/s of bandwidth, which sets how fast it generates text. At 32k context it runs 64 of the 128 open models we track fully in memory; the most capable is Qwen 3.8 27B at Q8_0, at about 19 tok/s (estimated). The best new price for the NVIDIA GeForce RTX 3090 in the US is $1,698 at Amazon; used, it starts at $1,549 (asking price).
Updated . Speeds are estimates; how they are worked out.
Prices
Every retailer we track in the US, cheapest first. Buy links may earn us a commission.
| Retailer | Condition | Price | Stock | Checked | Buy |
|---|---|---|---|---|---|
| eBayNVIDIA GeForce RTX 3090 Founders Edition FE 24GB GDDR6X Tested | used, asking price | $1,549 | In stock | 2 h ago | Buy |
| eBayZOTAC GeForce RTX 3090 24GB GDDR6X Trinity OC Graphics Card | refurbished | $1,599 | In stock | 2 h ago | Buy |
| eBayEVGA GeForce RTX 3090 FTW3 Ultra 24GB GDDR6X Graphics Card- Dust/Corrosion | used, asking price | $1,599 | In stock | 5 h ago | Buy |
| eBayNVIDIA GeForce RTX 3090 Founders Edition 24GB GDDR6 Graphics Card- Runs Hot | used, asking price | $1,599 | In stock | 5 h ago | Buy |
| eBayDell NVIDIA GeForce RTX 3090 24GB GDDR6X Graphics Card | used, asking price | $1,600 | In stock | 5 h ago | Buy |
| eBayEVGA GeForce RTX 3090 FTW3 ULTRA GAMING 24GB GDDR6X 24G-P5-3987-KR | used, asking price | $1,600 | In stock | 5 h ago | Buy |
| AmazonGIGABYTE GeForce RTX 3090 Gaming OC 24G Graphics Card | New | $1,698 | In stock | 36 min ago | Buy |
| AmazonPNY GeForce RTX 3090 24GB XLR8 Gaming Revel Epic-X RGB Triple Fan Graphics Card | New | $1,700 | In stock | 23 min ago | Buy |
| AmazonGigabyte GeForce RTX 3090 EAGLE OC 24G Graphics Card | refurbished | $1,700 | In stock | 23 min ago | Buy |
| AmazonGIGABYTE MSI Gaming GeForce RTX 3090 24GB GDRR6X 384-Bit HDMI/DP Nvlink Torx… | New | $1,700 | In stock | 3 h ago | Buy |
| AmazonZOTAC Gaming GeForce RTX 3090 Trinity OC 24GB GDDR6X 384-bit 19.5 Gbps PCIE… | refurbished | $1,730 | In stock | 23 min ago | Buy |
| AmazonGIGABYTE GeForce RTX 3090 Eagle OC 24G Graphics Card | New | $1,777 | In stock | 23 min ago | Buy |
| Amazonmsi Gaming GeForce RTX 3090 24GB GDRR6X 384-Bit HDMI/DP Nvlink Tri-Frozr 2… | New | $1,784 | In stock | 23 min ago | Buy |
| AmazonGigabyte 24GB NVIDIA GeForce RTX 3090 Turbo GDDR6X Graphics Card Model… | refurbished | $1,795 | In stock | 23 min ago | Buy |
| eBayUsed GeForce RTX 3090 on eBay | used, asking price | $1,799 | In stock | 14 min ago | Buy |
| AmazonnVidia GeForce RTX 3090 Founders Edition Graphics Card | New | $1,799 | In stock | 23 min ago | Buy |
| AmazonGIGABYTE AORUS GeForce RTX 3090 Master 24G | New | $1,800 | In stock | 23 min ago | Buy |
| AmazonEVGA 24G-P5-3975-KR GeForce RTX 3090 XC3 Ultra Gaming | refurbished | $1,850 | In stock | 36 min ago | Buy |
| AmazonGigabyte GeForce RTX 3090 GAMING OC 24G Graphics Card | refurbished | $1,880 | In stock | 23 min ago | Buy |
| AmazonASUS ROG STRIX NVIDIA GeForce RTX 3090 Gaming Graphics Card- PCIe 4.0 | refurbished | $1,900 | In stock | 23 min ago | Buy |
| AmazonMSI Gaming GeForce RTX 3090 24GB GDRR6X 384-Bit HDMI/DP Nvlink Torx Fan 3… | refurbished | $1,900 | In stock | 23 min ago | Buy |
| AmazonMSI Gaming GeForce RTX 3090 24GB GDRR6X 384-Bit HDMI/DP Nvlink Tri-Frozr 2… | refurbished | $1,900 | In stock | 23 min ago | Buy |
| AmazonASUS ROG Strix NVIDIA GeForce RTX 3090 White OC Edition Gaming Graphics Card | refurbished | $1,900 | In stock | 23 min ago | Buy |
| AmazonPNY 2021 GeForce RTX 3090 24GB XLR8 Gaming Uprising EPIC-X RGB Triple Fan… | refurbished | $1,900 | In stock | 23 min ago | Buy |
| AmazonNVIDIA GeForce RTX 3090 Founders Edition Graphics Card | refurbished | $1,950 | In stock | 23 min ago | Buy |
| AmazonGIGABYTE GeForce RTX 3090 Vision OC 24G Graphics Card | refurbished | $1,950 | In stock | 23 min ago | Buy |
| AmazonPNY GeForce RTX 3090 24GB XLR8 Gaming REVEL EPIC-X RGB Triple Fan Graphics Card | refurbished | $1,950 | In stock | 23 min ago | Buy |
| AmazonEVGA GeForce RTX 3090 FTW3 Ultra Gaming | New | $1,950 | In stock | 23 min ago | Buy |
| AmazonASUS ROG Strix GeForce RTX 3090 OC Edition 24GB GDDR6X Gaming Graphics Card… | refurbished | $1,950 | In stock | 23 min ago | Buy |
| eBay✅SEALED EVGA GeForce RTX 3090 FTW3 Ultra ✅🔥Fast Shipping! 🔥 24G-P5-3987-KR ✅ | New | $1,999 | In stock | 2 h ago | Buy |
| AmazonASUS TUF Gaming NVIDIA GeForce RTX 3090 OC Edition Graphics Card- PCIe 4.0 | refurbished | $2,100 | In stock | 23 min ago | Buy |
| eBayMSI Ventus Gaming GeForce RTX 3090 24GB GDRR6X 384-Bit HDMI/DP Nvlink Torx Fan 3 | New | $2,150 | In stock | 5 h ago | Buy |
| eBayEVGA GeForce RTX 3090 KINGPIN Graphics Card | New | $2,250 | In stock | 5 h ago | Buy |
| eBay✅NEW ASUS TUF GeForce RTX 3090 24GB GDDR6X 🔥 SEALED *IN HAND FAST 2DAY SHIP🚐 | New | $2,399 | In stock | 2 h ago | Buy |
| AmazonEVGA GeForce RTX 3090 FTW3 Ultra Gaming | New | $2,495 | In stock | 23 min ago | Buy |
| eBayASUS TUF Gaming GeForce RTX 3090 NON LHR OC 24GB GPU FAST/FREE SHIPPING✅🚚💨 | New | $2,500 | In stock | 2 h ago | Buy |
| eBayNVIDIA GeForce RTX 3090 Founders Edition 24GB GDDR6 Graphics Card NON-LHR | New | $2,500+ $100 delivery | In stock | 2 h ago | Buy |
| AmazonGigabyte 24GB NVIDIA GeForce RTX 3090 Turbo GDDR6X Graphics Card Model… | New | $2,795 | In stock | 36 min ago | Buy |
| Amazonmsi Gaming GeForce RTX 3090 24GB GDRR6X 384-Bit HDMI/DP 1875 MHz Ampere… | New | $2,799 | In stock | 23 min ago | Buy |
| AmazonGIGABYTE GeForce RTX 3090 Vision OC 24G Graphics Card | New | $2,799 | In stock | 23 min ago | Buy |
| AmazonASUS ROG STRIX NVIDIA GeForce RTX 3090 White OC Edition Gaming Graphics Card | New | $2,799 | In stock | 23 min ago | Buy |
| eBayMSI GEFORCE RTX 3090 VENTUS 3X 24G OC GPU GRAPHICS CARD 912-V388-055-RETAIL | New | $2,895 | In stock | 5 h ago | Buy |
| eBayEVGA GeForce RTX 3090 FTW3 Ultra 24GB GDDR6X Graphics Card | New | $1,600 | Out of stock | 2 h ago | Buy |
| eBayZOTAC NVIDIA GeForce RTX 3090 Trinity 24GB GDDR6X Graphics Card | New | $2,000+ $20 delivery | Out of stock | 5 h ago | Buy |
| eBayGIGABYTE GeForce RTX 3090 TURBO 24GB GDDR6X Graphics Card | New | $2,199 | Out of stock | 5 h ago | Buy |
Used on eBay: median asking price $1,799, most between $1,699 and $2,000 (117 listings, 2026-10-30). Used price history
Price history
Lowest price shown each day over the last 90 days.
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 @32k | Prefill | Good for |
|---|---|---|---|---|---|---|---|
| Qwen 3.8 27B Alibaba Qwen | Q8_0 | fits | 30.5 GB | 256k | 19tok/sest. | 515 tok/s | chat, long documents |
| Qwen 3.5 122B-A10B Alibaba Qwen | UD-Q2_K_XL | fits | 41.1 GB | 224k256k with q8 cache | 81tok/sest. | 1208 tok/s | chat, coding, agents, long documents |
| Qwen 3.6 27B Alibaba Qwen | Q8_0 | fits | 30.1 GB | 256k | 19tok/sest. | 515 tok/s | chat, long documents |
| Gemma 4 31B | Q8_0 | fits | 35.0 GB | 172k256k with q8 cache | 16tok/sest. | 459 tok/s | chat |
| Mistral Small 4 119B Mistral AI | UD-Q2_K_XL | fits | 39.4 GB | 296k471k with q8 cache | 111tok/sest. | 1343 tok/s | chat, coding, agents, long documents |
| Qwen 3.6 35B-A3B Alibaba Qwen | Q8_0 | fits | 36.3 GB | 256k | 91tok/sest. | 3679 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 27B Alibaba Qwen | Q8_0 | fits | 30.1 GB | 256k | 19tok/sest. | 515 tok/s | chat, long documents |
| Gemma 4 26B-A4B | Q8_0 | fits | 27.1 GB | 256k | 69tok/sest. | 3273 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q8_0 | fits | 36.3 GB | 256k | 91tok/sest. | 3679 tok/s | chat, coding, agents, long documents |
| GLM 4.7 Flash Z.ai | Q8_0 | fits | 32.6 GB | 198k | 49tok/sest. | 1921 tok/s | chat, coding, agents, long documents |
| Devstral Small 2 24B Mistral AI | Q8_0 | fits | 29.6 GB | 137k251k with q8 cache | 19tok/sest. | 544 tok/s | chat |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | UD-Q6_K_XL | fits | 34.1 GB | 256k | 97tok/sest. | 4198 tok/s | chat, coding, agents, long documents |
| Kimi Linear 48B-A3B Moonshot AI | Q6_K | fits | 39.3 GB | 588k802k with q8 cache | 125tok/sest. | 3171 tok/s | chat, coding, long documents |
| gpt-oss 20B OpenAI | MXFP4 | fits | 13.3 GB | 128k | 108tok/sest. | 2747 tok/s | chat, coding, agents, long documents |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q8_0 | fits | 34.5 GB | 155k256k with q8 cache | 54tok/sest. | 1692 tok/s | chat, coding, agents, long documents |
| Qwen3 32B Alibaba Qwen | Q8_0 | fits | 41.7 GB | 40k | 13tok/sest. | 320 tok/s | chat |
| Gemma 4 12B | Q8_0 | fits | 13.9 GB | 256k | 43tok/sest. | 1195 tok/s | chat, coding, long documents |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 11.2 GB | 256k | 55tok/sest. | 1489 tok/s | chat, coding, long documents |
| Mistral Small 3.2 24B Mistral AI | Q8_0 | fits | 29.6 GB | 128k | 19tok/sest. | 544 tok/s | chat |
| Gemma 3 27B | Q8_0 | fits | 30.9 GB | 128k | 18tok/sest. | 547 tok/s | chat |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q8_0 | fits | 41.7 GB | 51k95k with q8 cache | 13tok/sest. | 367 tok/s | chat |
| Ministral 3 14B Mistral AI | Q8_0 | fits | 19.7 GB | 199k256k with q8 cache | 29tok/sest. | 827 tok/s | chat, coding, long documents |
| Qwen3 14B Alibaba Qwen | Q8_0 | fits | 20.9 GB | 40k | 28tok/sest. | 744 tok/s | chat, coding, long documents |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q8_0 | fits | 13.9 GB | 128k | 43tok/sest. | 1227 tok/s | chat, coding, long documents |
| Qwen3 8B Alibaba Qwen | Q8_0 | fits | 13.9 GB | 40k | 43tok/sest. | 1227 tok/s | chat, coding, long documents |
| Phi-4 14B Microsoft | Q8_0 | fits | 22.0 GB | 16k | 26tok/sest. | 748 tok/s | chat, coding |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 6.5 GB | 256k | 104tok/sest. | 2786 tok/s | chat, coding, long documents |
| Ministral 3 8B Mistral AI | Q8_0 | fits | 13.9 GB | 256k | 43tok/sest. | 1185 tok/s | chat, coding, long documents |
| Granite 4.2 8B IBM | Q8_0 | fits | 15.0 GB | 128k | 39tok/sest. | 1128 tok/s | chat, coding, agents, long documents |
| Gemma 4 E4B | Q8_0 | fits | 9.8 GB | 128k | 63tok/sest. | 1871 tok/s | chat, coding, long documents |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 11.2 GB | 125k | 130tok/sest. | 6119 tok/s | chat, coding, long documents |
| Llama 3.1 8B Meta | Q6_K | fits | 11.4 GB | 128k | 53tok/sest. | 1296 tok/s | chat, coding, long documents |
| Qwen2.5 0.5B Alibaba Qwen | Q8_0 | fits | 2.2 GB | 32k | 622tok/sest. | 13327 tok/s | chat, coding, long documents |
| Qwen3.5 0.8B Alibaba Qwen | Q8_0 | fits | 2.4 GB | 256k | 471tok/sest. | 12519 tok/s | chat, coding, agents, long documents |
| Qwen3.5 2B Alibaba Qwen | Q5_K_M | fits | 3.0 GB | 256k | 313tok/sest. | 5968 tok/s | chat, coding, agents, long documents |
| LFM3 1.7B Liquid AI | Q8_0 | fits | 3.4 GB | 256k | 257tok/sest. | 7429 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 1.5B DeepSeek | Q8_0 | fits | 3.9 GB | 128k | 205tok/sest. | 5014 tok/s | chat, coding, long documents |
| MiniCPM5 2B openbmb | Q8_0 | fits | 5.1 GB | 128k | 142tok/sest. | 2994 tok/s | chat, coding, agents, long documents |
| Spark X2.5 4B XHToken | mlx-4bit | fits | 5.3 GB | 1024k | 135tok/sest. | 2940 tok/s | chat, coding, agents, long documents |
| LFM2.5 2.6B Liquid AI | Q8_0 | fits | 5.8 GB | 128k | 119tok/sest. | 3391 tok/s | chat, coding, agents, long documents |
| LFM2.5 VL 3B Liquid AI | Q8_0 | fits | 5.8 GB | 32k | 119tok/sest. | 3110 tok/s | chat, coding, agents, long documents |
| Mellum2.1 12B A2.5B Thinking JetBrains | Q8_0 | fits | 13.8 GB | 128k | 110tok/sest. | 4418 tok/s | chat, coding, agents, long documents |
| FrogNano 4B 2609 Microsoft | Q8_0 | fits | 6.6 GB | 256k | 101tok/sest. | 2786 tok/s | chat, coding, agents, long documents |
| granite vision 4.1 4b IBM | Q8_0 | fits | 7.2 GB | 128k | 92tok/sest. | 2173 tok/s | chat, coding, long documents |
| granite 4.2 3b IBM | Q8_0 | fits | 7.4 GB | 128k | 88tok/sest. | 2277 tok/s | chat, coding, agents, long documents |
| Kimi VL A3B Thinking 2506 Moonshot AI | Q8_0 | fits | 18.0 GB | 128k | 85tok/sest. | 3320 tok/s | chat, coding, long documents |
| Kimi VL A3B Moonshot AI | mlx-8bit | fits | 18.8 GB | 128k | 81tok/sest. | 2794 tok/s | chat, coding, agents, long documents |
| Ministral 3 3B Instruct 2512 Mistral AI | Q8_0 | fits | 7.9 GB | 256k | 81tok/sest. | 2177 tok/s | chat, coding, agents, long documents |
| LFM2.5 24B A2B Liquid AI | Q8_0 | fits | 27.5 GB | 128k | 72tok/sest. | 3410 tok/s | chat, coding, agents, long documents |
| GLM 4 9B 0414 Z.ai | mlx-5bit | fits | 10.2 GB | 32k | 61tok/sest. | 1082 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 7B DeepSeek | Q8_0 | fits | 10.6 GB | 128k | 58tok/sest. | 1465 tok/s | chat, coding, long documents |
| GLM 4.6V Flash Z.ai | Q8_0 | fits | 11.9 GB | 128k | 51tok/sest. | 1020 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Llama 8B DeepSeek | Q8_0 | fits | 13.2 GB | 128k | 45tok/sest. | 1296 tok/s | chat, coding, long documents |
| GLM 4.1V 9B Thinking Z.ai | mlx-8bit | fits | 13.5 GB | 64k | 44tok/sest. | 1020 tok/s | chat, coding, long documents |
| Ministral 3 8B Reasoning 2512 Mistral AI | Q8_0 | fits | 13.9 GB | 256k | 43tok/sest. | 1185 tok/s | chat, coding, agents, long documents |
| Ministral 3 14B Reasoning 2512 Mistral AI | Q8_0 | fits | 19.7 GB | 199k256k with q8 cache | 29tok/sest. | 827 tok/s | chat, coding, long documents |
| DeepSeek R1 Distill Qwen 14B DeepSeek | Q8_0 | fits | 21.9 GB | 128k | 26tok/sest. | 700 tok/s | chat, coding |
| Qwen3.8 27B OBLITERATED OBLITERATUS | mlx-4bit | fits | 22.7 GB | 256k | 25tok/sest. | 515 tok/s | chat, coding, long documents |
| Devstral Small 2507 Mistral AI | Q8_0 | fits | 29.6 GB | 128k | 19tok/sest. | 552 tok/s | chat |
| Magistral Small 2506 Mistral AI | Q8_0 | fits | 29.6 GB | 40k | 19tok/sest. | 552 tok/s | chat |
| Magistral Small 2507 Mistral AI | Q8_0 | fits | 29.6 GB | 40k | 19tok/sest. | 552 tok/s | chat |
| Magistral Small 2509 Mistral AI | Q8_0 | fits | 29.6 GB | 128k | 19tok/sest. | 544 tok/s | chat |
| Muse Glimmer 30B meta-models | Q8_0 | fits | 31.9 GB | 128k | 18tok/sest. | 497 tok/s | chat, long documents |
| granite 4.2 30b IBM | Q8_0 | fits | 38.3 GB | 65k120k with q8 cache | 15tok/sest. | 422 tok/s | chat |
| Qwen3 Coder Next Alibaba Qwen | Q4_K_M | offload | 47.3 GB | 14k23k with q8 cache | 97tok/sest. | 2893 tok/s | chat, coding, agents, long documents |
| Nemotron 3 Super 120B-A12B NVIDIA | UD-Q2_K_XL | offload | 52.6 GB | – | 29tok/sest. | 1139 tok/s | chat, coding, long documents |
| gpt-oss 120B OpenAI | Q4_K_M | offload | 60.9 GB | – | 24tok/sest. | 1675 tok/s | chat, coding |
| GLM 4.5 Air Z.ai | Q2_K | offload | 49.2 GB | 18k34k with q8 cache | 20tok/sest. | 484 tok/s | chat |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q4_K_M | offload | 47.3 GB | 15k24k with q8 cache | 118tok/sest. | 3443 tok/s | chat, coding, agents, long documents |
| Llama 3.3 70B Meta | Q4_K_M | offload | 50.9 GB | 19k35k with q8 cache | 6tok/sest. | 165 tok/s | – |
| GLM 4.5V Z.ai | Q4_K_M | offload | 66.3 GB | – | 6tok/sest. | 399 tok/s | – |
| DeepSeek R1 Distill Llama 70B DeepSeek | Q4_K_M | offload | 50.9 GB | 19k35k with q8 cache | 6tok/sest. | 165 tok/s | – |
| GLM 4.6V Z.ai | Q4_K_M | offload | 72.6 GB | – | 5tok/sest. | 381 tok/s | – |
| Kimi Dev 72B Moonshot AI | Q6_K | offload | 71.2 GB | – | 2tok/sest. | 134 tok/s | – |
| DeepSeek V4 Flash DeepSeek | UD-Q2_K_XL | won't run | 94.2 GB | – | – | – | – |
| GLM 5.3 Flash Z.ai | UD-Q2_K_XL | won't run | 103.0 GB | – | – | – | – |
| Qwen 3.8 Flash Next Alibaba Qwen | UD-Q2_K_XL | won't run | 75.6 GB | – | – | – | – |
| MiniMax M2.7 MiniMax | UD-Q2_K_XL | won't run | 79.2 GB | – | – | – | – |
| DeepSeek R1 DeepSeek | Q4_K_M | won't run | 380.1 GB | – | – | – | – |
| DeepSeek R1 0528 DeepSeek | Q4_K_M | won't run | 380.6 GB | – | – | – | – |
| DeepSeek R1 Zero DeepSeek | Q4_K_M | won't run | 380.1 GB | – | – | – | – |
| DeepSeek V3 DeepSeek | Q4_K_M | won't run | 380.1 GB | – | – | – | – |
| DeepSeek V3 0324 DeepSeek | Q4_K_M | won't run | 380.1 GB | – | – | – | – |
| DeepSeek V3.1 DeepSeek | Q4_K_M | won't run | 381.0 GB | – | – | – | – |
| DeepSeek V3.1 Terminus DeepSeek | Q4_K_M | won't run | 381.0 GB | – | – | – | – |
| DeepSeek V3.2 DeepSeek | Q4_K_M | won't run | 381.0 GB | – | – | – | – |
| DeepSeek V4 Flash 0731 DeepSeek | MXFP4 | won't run | 149.6 GB | – | – | – | – |
| DeepSeek V4 Flash Vision Exp DeepSeek | MXFP4 | won't run | 158.4 GB | – | – | – | – |
| Devstral 2 123B Instruct 2512 Mistral AI | Q4_K_M | won't run | 82.0 GB | – | – | – | – |
| GLM 4.5 Z.ai | Q4_K_M | won't run | 214.4 GB | – | – | – | – |
| GLM 4.6 Z.ai | Q4_K_M | won't run | 213.6 GB | – | – | – | – |
| GLM 4.7 Z.ai | Q4_K_M | won't run | 214.4 GB | – | – | – | – |
| GLM 5 Z.ai | MXFP4 | won't run | 386.4 GB | – | – | – | – |
| GLM 5.1 Z.ai | MXFP4 | won't run | 424.0 GB | – | – | – | – |
| GLM 5.2 Z.ai | UD-Q4_K_M | won't run | 437.9 GB | – | – | – | – |
| GLM 5.3 Z.ai | Q8_0 | won't run | 750.4 GB | – | – | – | – |
| Kimi K2 Moonshot AI | Q4_K_M | won't run | 581.6 GB | – | – | – | – |
| Kimi K2 Instruct 0905 Moonshot AI | Q4_K_M | won't run | 582.0 GB | – | – | – | – |
| Kimi K2 Thinking Moonshot AI | Q4_K_M | won't run | 582.0 GB | – | – | – | – |
| Kimi K2.5 Moonshot AI | Q4_K_M | won't run | 582.0 GB | – | – | – | – |
| MiniMax M2 MiniMax | Q4_K_M | won't run | 137.9 GB | – | – | – | – |
| MiniMax M2.1 MiniMax | Q4_K_M | won't run | 137.9 GB | – | – | – | – |
| MiniMax M2.5 MiniMax | MXFP4 | won't run | 124.3 GB | – | – | – | – |
| MiniMax M3 MiniMax | MXFP4 | won't run | 244.7 GB | – | – | – | – |
| Mistral Medium 3.5 128B Mistral AI | Q4_K_M | won't run | 82.0 GB | – | – | – | – |
Specifications
From the manufacturer's published specifications; sources are linked where we have them.
- GPU
- GeForce RTX 3090
- Memory
- 24 GB GDDR6X
- Memory bus
- 384-bit
- Memory bandwidth
- 936 GB/s
- FP16 compute
- 71 TFLOPS
- Software
- CUDA
- Board power
- 350 W
- PCIe generation
- Gen 4
- PCIe lanes
- x16
- Parts in our builds with it
- AMD Ryzen 7 7700, AMD Ryzen 9 9900X, MSI MAG B650 Tomahawk WiFi, ASUS ProArt X870E-Creator WiFi, Fractal Design North, Fractal Design Torrent, Corsair RM850x ATX 3.1 850W, Seasonic Vertex GX-1200 1200W, G.Skill Flare X5 64GB (2×32GB) DDR5-6000, Corsair Vengeance 128GB (4×32GB) DDR5-5200, Samsung 990 Pro 2TB
Compare with
Questions
- How much memory does the NVIDIA GeForce RTX 3090 have for AI models?
- The NVIDIA GeForce RTX 3090 has 24 GB of GDDR6X memory with 936 GB/s of bandwidth, which sets how fast it generates text.
- What is the best model the NVIDIA GeForce RTX 3090 can run locally?
- Qwen 3.8 27B (Q8_0) fits fully in its memory at 32k context and generates at about 19 tok/s, an estimate from its memory bandwidth. 64 of the 128 models we track fit at that context.
- Can the NVIDIA GeForce RTX 3090 run DeepSeek V4 Flash?
- No: even at UD-Q2_K_XL, DeepSeek V4 Flash needs about 94 GB at 32k context, more than the NVIDIA GeForce RTX 3090 and system RAM can hold.
- How much does the NVIDIA GeForce RTX 3090 cost in the US?
- The best new price for the NVIDIA GeForce RTX 3090 in the US is $1,698 at Amazon; used, it starts at $1,549 (asking price).
Speeds on this page are for 32k context. See the best hardware for local AI at every budget.