NVIDIA GeForce RTX 5080
16 GB · 960 GB/s · 360 W
In short
The NVIDIA GeForce RTX 5080 has 16 GB of GDDR7 memory with 960 GB/s of bandwidth, which sets how fast it generates text. At 64k context it runs 26 of the 113 open models we track fully in memory; the most capable is gpt-oss 20B at MXFP4, at about 88 tok/s (estimated). The best new price for the NVIDIA GeForce RTX 5080 in Canada is $2,370 at Amazon; used, it starts at $2,850 (asking price).
Updated . Speeds are estimates; how they are worked out.
Prices
Every retailer we track in Canada, cheapest first. Buy links may earn us a commission.
| Retailer | Condition | Price | Stock | Checked | Buy |
|---|---|---|---|---|---|
| AmazonThe SFF-Ready ASUS Prime GeForce RTX 5080 16GB GDDR7 OC Edition Graphics Card | New | $2,370 | In stock | 1 h ago | Buy |
| AmazonASUS Prime GeForce RTX 5080 EVO 16GB GDDR7 OC Edition Gaming Graphics Card | New | $2,420 | In stock | 1 h ago | Buy |
| AmazonMSI Gaming RTX 5080 16G Ventus 3X OC White Graphics Card | New | $2,580 | In stock | 1 h ago | Buy |
| Amazonmsi Gaming RTX 5080 16G Ventus 3X OC Black Graphics Card | New | $2,640 | In stock | 1 h ago | Buy |
| AmazonASUS TUF Gaming GeForce RTX 5080 16GB GDDR7 BTF OC Edition Gaming Graphics Card | New | $2,650 | In stock | 1 h ago | Buy |
| eBayASUS TUF GAMING GeForce RTX 5080 16GB Oc New In Hand Shipping To Canada USA | New | $2,570+ $114 delivery | In stock | 2 h ago | Buy |
| AmazonASUS ProArt GeForce RTX 5080 16GB GDDR7 OC Edition Graphics Card | New | $2,700 | In stock | 1 h ago | Buy |
| AmazonGigabyte GeForce RTX 5080 Gaming OC 16G Graphics Card | New | $2,718 | In stock | 1 h ago | Buy |
| Amazonmsi Gaming RTX 5080 16G Inspire 3X OC Black Graphics Card | New | $2,720 | In stock | 1 h ago | Buy |
| eBayNEW Gigabyte RTX 5080 WINDFORCE SFF 16GB GDDR7 SFF-Ready | New | $2,700+ $30 delivery | In stock | 2 h ago | Buy |
| AmazonMSI Gaming RTX 5080 16G Gaming Trio OC White Graphics Card | New | $2,750 | In stock | 1 h ago | Buy |
| eBayASUS ROG Astral RTX 5080 16GB GDDR7 In White | New | $2,750 | In stock | 2 h ago | Buy |
| AmazonPNY NVIDIA GeForce RTX 5080 Slim Dual-Fan Dual-Slot OC Graphics Card | New | $2,763 | In stock | 1 h ago | Buy |
| eBayNVIDIA GeForce RTX 5080 16GB GDDR7 Founders Edition | used, asking price | $2,850 | In stock | 2 h ago | Buy |
| AmazonASUS ROG Astral GeForce RTX 5080 16GB GDDR7 OC Edition Gaming Graphics Card | New | $2,920 | In stock | 1 h ago | Buy |
| AmazonAsus Prime GeForce RTX 5080 16GB GDDR7 Prime-RTX5080-16G Pci-Express 5.0 Dlss… | New | $2,940 | In stock | 1 h ago | Buy |
| AmazonMSI Gaming RTX 5080 16G SUPRIM Liquid SOC Graphics Card | New | $2,950 | In stock | 1 h ago | Buy |
| eBayAORUS Master RTX 5080 Graphics Card | New | $2,999 | In stock | 2 h ago | Buy |
| AmazonGIGABYTE AORUS GeForce RTX 5080 Master ICE 16G Graphics Card | New | $3,000 | In stock | 1 h ago | Buy |
| eBayAsus ROG Astral GeForce RTX 5080 16GB GDDR7 OC Edition | New | $3,000 | In stock | 2 h ago | Buy |
| AmazonASUS ROG Astral GeForce RTX 5080 16GB GDDR7 White OC Edition Graphics Card | New | $3,060 | In stock | 1 h ago | Buy |
| eBayASUS PRIME GeForce RTX 5080 OC 16GB / Gaming Graphics Card | New | $3,100+ $160 delivery | In stock | 2 h ago | Buy |
| eBayMSI GeForce RTX 5080 Gaming Trio OC 16GB GDDR7 Video Card | New | $3,500+ $60 delivery | In stock | 2 h ago | Buy |
| eBayASUS TUF GAMING GeForce RTX 5080 16GB Oc New In Hand Shipping To Canada + USA | New | $3,700 | In stock | 2 h ago | Buy |
| eBayAsus ROG Astral GeForce RTX 5080 16GB GDDR7 OC HATSUNE MIKU EDITION | New | $7,000 | In stock | 2 h ago | Buy |
Price history
Lowest price shown each day over the last 90 days.
Not enough price history yet.
What it runs
Every model in the catalogue, with the best quant for this hardware. Estimates, not measurements.
| Model | Quant | Fits | Memory | Max context | Decode @64k | Prefill | Good for |
|---|---|---|---|---|---|---|---|
| gpt-oss 20B OpenAI | MXFP4 | fits | 13.9 GB | 116k128k with q8 cache | 88tok/sest. | 3423 tok/s | chat, coding, agents, long documents |
| Gemma 4 12B | Q8_0 | fits | 14.2 GB | 120k193k with q8 cache | 42tok/sest. | 1760 tok/s | chat, coding, long documents |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 12.0 GB | 155k256k with q8 cache | 51tok/sest. | 2155 tok/s | chat, coding, long documents |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q4_K_M | fits | 14.8 GB | 68k124k with q8 cache | 41tok/sest. | 1424 tok/s | chat, coding |
| Qwen3 8B Alibaba Qwen | Q4_K_M | fits | 14.8 GB | 40k | 41tok/sest. | 1424 tok/s | chat, coding |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 7.3 GB | 256k | 89tok/sest. | 3735 tok/s | chat, coding, long documents |
| Ministral 3 8B Mistral AI | Q5_K_M | fits | 15.2 GB | 65k118k with q8 cache | 39tok/sest. | 1409 tok/s | chat, coding |
| Gemma 4 E4B | Q8_0 | fits | 10.5 GB | 128k | 59tok/sest. | 2822 tok/s | chat, coding, long documents |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 12.5 GB | 119k125k with q8 cache | 83tok/sest. | 6023 tok/s | chat, coding, long documents |
| Llama 3.1 8B Meta | Q6_K | fits | 15.2 GB | 65k118k with q8 cache | 39tok/sest. | 1530 tok/s | chat, coding |
| Qwen2.5 0.5B Alibaba Qwen | Q8_0 | fits | 2.3 GB | 32k | 445tok/sest. | 13358 tok/s | chat, coding, long documents |
| Qwen3.5 0.8B Alibaba Qwen | Q8_0 | fits | 2.6 GB | 256k | 364tok/sest. | 15145 tok/s | chat, coding, agents, long documents |
| Qwen3.5 2B Alibaba Qwen | Q5_K_M | fits | 3.2 GB | 256k | 263tok/sest. | 8257 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 1.5B DeepSeek | Q8_0 | fits | 4.6 GB | 128k | 158tok/sest. | 5532 tok/s | chat, coding, long documents |
| MiniCPM5 2B openbmb | Q8_0 | fits | 6.2 GB | 128k | 108tok/sest. | 3118 tok/s | chat, coding, agents, long documents |
| Mellum2.1 12B A2.5B Thinking JetBrains | Q8_0 | fits | 14.0 GB | 128k | 98tok/sest. | 5582 tok/s | chat, coding, agents, long documents |
| LFM2.5 2.6B Liquid AI | Q8_0 | fits | 7.5 GB | 128k | 86tok/sest. | 3781 tok/s | chat, coding, agents, long documents |
| LFM2.5 VL 3B Liquid AI | Q8_0 | fits | 7.5 GB | 32k | 86tok/sest. | 3556 tok/s | chat, coding, agents, long documents |
| Kimi VL A3B Moonshot AI | mlx-5bit | fits | 14.0 GB | 103k128k with q8 cache | 85tok/sest. | 3838 tok/s | chat, coding, agents, long documents |
| granite vision 4.1 4b IBM | Q8_0 | fits | 9.4 GB | 128k | 66tok/sest. | 2374 tok/s | chat, coding, long documents |
| granite 4.2 3b IBM | Q8_0 | fits | 9.7 GB | 128k | 64tok/sest. | 2452 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 7B DeepSeek | Q8_0 | fits | 12.1 GB | 118k128k with q8 cache | 50tok/sest. | 1792 tok/s | chat, coding, long documents |
| GLM 4.6V Flash Z.ai | Q8_0 | fits | 12.9 GB | 119k128k with q8 cache | 47tok/sest. | 1209 tok/s | chat, coding, agents, long documents |
| GLM 4.1V 9B Thinking Z.ai | mlx-8bit | fits | 14.5 GB | 64k | 41tok/sest. | 1209 tok/s | chat, coding, long documents |
| DeepSeek R1 Distill Llama 8B DeepSeek | Q6_K | fits | 15.2 GB | 65k118k with q8 cache | 39tok/sest. | 1530 tok/s | chat, coding |
| Ministral 3 8B Reasoning 2512 Mistral AI | Q5_K_M | fits | 15.2 GB | 65k118k with q8 cache | 39tok/sest. | 1409 tok/s | chat, coding, agents |
| Qwen 3.8 27B Alibaba Qwen | UD-Q4_K_M | offload | 20.5 GB | – | 8tok/sest. | 625 tok/s | chat |
| Qwen 3.6 27B Alibaba Qwen | Q4_K_M | offload | 20.9 GB | – | 7tok/sest. | 620 tok/s | chat |
| Gemma 4 31B | Q4_K_M | offload | 23.9 GB | – | 5tok/sest. | 527 tok/s | – |
| Mistral Small 4 119B Mistral AI | UD-Q2_K_XL | offload | 39.9 GB | – | 13tok/sest. | 944 tok/s | chat |
| Qwen 3.6 35B-A3B Alibaba Qwen | MXFP4 | offload | 22.6 GB | – | 25tok/sest. | 3575 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 27B Alibaba Qwen | Q4_K_M | offload | 20.8 GB | – | 8tok/sest. | 621 tok/s | chat |
| Gemma 4 26B-A4B | UD-Q4_K_M | offload | 18.3 GB | – | 32tok/sest. | 4116 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q4_K_M | offload | 22.9 GB | – | 25tok/sest. | 3552 tok/s | chat, coding, agents, long documents |
| GLM 4.7 Flash Z.ai | Q4_K_M | offload | 21.4 GB | – | 14tok/sest. | 1824 tok/s | chat, coding |
| Devstral Small 2 24B Mistral AI | Q4_K_M | offload | 24.4 GB | 8k15k with q8 cache | 5tok/sest. | 562 tok/s | chat |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | UD-Q6_K_XL | offload | 34.1 GB | – | 14tok/sest. | 3641 tok/s | chat |
| Kimi Linear 48B-A3B Moonshot AI | Q4_K_M | offload | 29.6 GB | – | 25tok/sest. | 2520 tok/s | chat, coding, long documents |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q4_K_M | offload | 24.4 GB | – | 9tok/sest. | 1231 tok/s | chat |
| Qwen3 32B Alibaba Qwen | Q4_K_M | offload | 35.5 GB | – | 2tok/sest. | 246 tok/s | – |
| Gemma 3 27B | Q4_K_M | offload | 21.9 GB | – | 6tok/sest. | 677 tok/s | chat |
| Mistral Small 3.2 24B Mistral AI | Q4_K_M | offload | 24.4 GB | 8k15k with q8 cache | 5tok/sest. | 562 tok/s | chat |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q4_K_M | offload | 35.6 GB | – | 2tok/sest. | 304 tok/s | – |
| Ministral 3 14B Mistral AI | Q4_K_M | offload | 18.7 GB | 43k79k with q8 cache | 11tok/sest. | 913 tok/s | chat, coding |
| Qwen3 14B Alibaba Qwen | Q4_K_M | offload | 19.5 GB | 38k40k with q8 cache | 9tok/sest. | 782 tok/s | chat, coding |
| Phi-4 14B Microsoft | Q4_K_M | offload | 21.9 GB | 16k | 7tok/sest. | 737 tok/s | chat, coding |
| Granite 4.2 8B IBM | Q4_K_M | offload | 16.2 GB | 58k107k with q8 cache | 24tok/sest. | 1259 tok/s | chat, coding, agents |
| LFM2.5 24B A2B Liquid AI | Q4_K_M | offload | 20.4 GB | 4k8k with q8 cache | 15tok/sest. | 2917 tok/s | chat, coding, agents |
| DeepSeek R1 Distill Qwen 14B DeepSeek | Q4_K_M | offload | 21.4 GB | 32k60k with q8 cache | 7tok/sest. | 677 tok/s | chat, coding |
| Devstral Small 2507 Mistral AI | Q4_K_M | offload | 24.4 GB | 8k15k with q8 cache | 5tok/sest. | 569 tok/s | chat |
| Magistral Small 2506 Mistral AI | Q4_K_M | offload | 24.4 GB | 8k15k with q8 cache | 5tok/sest. | 569 tok/s | chat |
| Magistral Small 2507 Mistral AI | Q4_K_M | offload | 24.4 GB | 8k15k with q8 cache | 5tok/sest. | 569 tok/s | chat |
| Magistral Small 2509 Mistral AI | Q4_K_M | offload | 24.4 GB | 8k15k with q8 cache | 5tok/sest. | 562 tok/s | chat |
| granite 4.2 30b IBM | Q4_K_M | offload | 33.9 GB | – | 3tok/sest. | 362 tok/s | – |
| DeepSeek V4 Flash DeepSeek | UD-Q2_K_XL | won't run | 96.6 GB | – | – | – | – |
| GLM 5.3 Flash Z.ai | UD-Q2_K_XL | won't run | 103.1 GB | – | – | – | – |
| Qwen 3.8 Flash Next Alibaba Qwen | UD-Q2_K_XL | won't run | 76.1 GB | – | – | – | – |
| MiniMax M2.7 MiniMax | UD-Q2_K_XL | won't run | 86.7 GB | – | – | – | – |
| Qwen 3.5 122B-A10B Alibaba Qwen | UD-Q2_K_XL | won't run | 41.7 GB | – | – | – | – |
| Nemotron 3 Super 120B-A12B NVIDIA | UD-Q2_K_XL | won't run | 52.6 GB | – | – | – | – |
| Qwen3 Coder Next Alibaba Qwen | Q4_K_M | won't run | 47.8 GB | – | – | – | – |
| gpt-oss 120B OpenAI | Q4_K_M | won't run | 61.8 GB | – | – | – | – |
| GLM 4.5 Air Z.ai | Q2_K | won't run | 54.8 GB | – | – | – | – |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q4_K_M | won't run | 47.8 GB | – | – | – | – |
| Llama 3.3 70B Meta | Q4_K_M | won't run | 60.7 GB | – | – | – | – |
| DeepSeek R1 DeepSeek | Q4_K_M | won't run | 382.0 GB | – | – | – | – |
| DeepSeek R1 0528 DeepSeek | Q4_K_M | won't run | 382.5 GB | – | – | – | – |
| DeepSeek R1 Distill Llama 70B DeepSeek | Q4_K_M | won't run | 60.7 GB | – | – | – | – |
| DeepSeek V3 0324 DeepSeek | Q4_K_M | won't run | 382.0 GB | – | – | – | – |
| DeepSeek V3.1 DeepSeek | Q4_K_M | won't run | 382.9 GB | – | – | – | – |
| DeepSeek V3.2 DeepSeek | Q4_K_M | won't run | 382.9 GB | – | – | – | – |
| DeepSeek V4 Flash 0731 DeepSeek | MXFP4 | won't run | 152.1 GB | – | – | – | – |
| DeepSeek V4 Flash Vision Exp DeepSeek | MXFP4 | won't run | 160.9 GB | – | – | – | – |
| Devstral 2 123B Instruct 2512 Mistral AI | Q8_0 | won't run | 146.8 GB | – | – | – | – |
| GLM 4.5V Z.ai | Q4_K_M | won't run | 71.8 GB | – | – | – | – |
| GLM 4.6V Z.ai | Q4_K_M | won't run | 78.2 GB | – | – | – | – |
| GLM 4.7 Z.ai | Q4_K_M | won't run | 225.7 GB | – | – | – | – |
| GLM 5.1 Z.ai | MXFP4 | won't run | 426.5 GB | – | – | – | – |
| GLM 5.2 Z.ai | UD-Q4_K_M | won't run | 440.4 GB | – | – | – | – |
| GLM 5.3 Z.ai | Q8_0 | won't run | 752.9 GB | – | – | – | – |
| Kimi K2 Moonshot AI | Q4_K_M | won't run | 583.5 GB | – | – | – | – |
| Kimi K2 Instruct 0905 Moonshot AI | Q4_K_M | won't run | 583.9 GB | – | – | – | – |
| Kimi K2 Thinking Moonshot AI | Q4_K_M | won't run | 583.9 GB | – | – | – | – |
| Kimi K2.5 Moonshot AI | Q4_K_M | won't run | 583.9 GB | – | – | – | – |
| MiniMax M2 MiniMax | Q4_K_M | won't run | 145.4 GB | – | – | – | – |
| MiniMax M2.1 MiniMax | Q4_K_M | won't run | 145.4 GB | – | – | – | – |
| MiniMax M2.5 MiniMax | MXFP4 | won't run | 131.8 GB | – | – | – | – |
| MiniMax M3 MiniMax | UD-Q4_K_M | won't run | 255.3 GB | – | – | – | – |
| Mistral Medium 3.5 128B Mistral AI | Q4_K_M | won't run | 92.8 GB | – | – | – | – |
Specifications
From the manufacturer's published specifications; sources are linked where we have them.
- GPU
- GeForce RTX 5080
- Memory
- 16 GB GDDR7
- Memory bus
- 256-bit
- Memory bandwidth
- 960 GB/s
- FP16 compute
- 113 TFLOPS
- Software
- CUDA
- Board power
- 360 W
- PCIe generation
- Gen 5
- PCIe lanes
- x16
Compare with
Questions
- How much memory does the NVIDIA GeForce RTX 5080 have for AI models?
- The NVIDIA GeForce RTX 5080 has 16 GB of GDDR7 memory with 960 GB/s of bandwidth, which sets how fast it generates text.
- What is the best model the NVIDIA GeForce RTX 5080 can run locally?
- gpt-oss 20B (MXFP4) fits fully in its memory at 64k context and generates at about 88 tok/s, an estimate from its memory bandwidth. 26 of the 113 models we track fit at that context.
- Can the NVIDIA GeForce RTX 5080 run DeepSeek V4 Flash?
- No: even at UD-Q2_K_XL, DeepSeek V4 Flash needs about 97 GB at 64k context, more than the NVIDIA GeForce RTX 5080 and system RAM can hold.
- How much does the NVIDIA GeForce RTX 5080 cost in Canada?
- The best new price for the NVIDIA GeForce RTX 5080 in Canada is $2,370 at Amazon; used, it starts at $2,850 (asking price).
Speeds on this page are for 64k context. See the best hardware for local AI at every budget.