NVIDIA GeForce RTX 5070
12 GB · 672 GB/s · 250 W
In short
The NVIDIA GeForce RTX 5070 has 12 GB of GDDR7 memory with 672 GB/s of bandwidth, which sets how fast it generates text. At 32k context it runs 23 of the 113 open models we track fully in memory; the most capable is Gemma 4 12B at Q6_K, at about 39 tok/s (estimated). The best new price for the NVIDIA GeForce RTX 5070 in Canada is $1,181 at Amazon; used, it starts at $1,150 (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 |
|---|---|---|---|---|---|
| eBayNVIDIA GeForce RTX 5070 12GB Founders Edition Graphics Card BRAND NEW Canada🇨🇦 | used, asking price | $1,150 | In stock | 2 h ago | Buy |
| AmazonGIGABYTE GeForce RTX 5070 AERO OC 12G Graphics Card | New | $1,181 | In stock | 7 h ago | Buy |
| AmazonPNY NVIDIA GeForce RTX 5070 Epic-X RGB OC Triple-Fan Graphics Card | New | $1,200 | In stock | 34 min ago | Buy |
| AmazonMSI Gaming RTX 5070 12G Shadow 2X OC Graphics Card | New | $1,259 | In stock | 34 min ago | Buy |
| AmazonASUS Prime GeForce RTX 5070 12GB GDDR7 OC Edition Gaming Graphics Card | New | $1,270 | In stock | 39 min ago | Buy |
| AmazonASUS The SFF-Ready Prime GeForce RTX 5070 12GB GDDR7 White OC Edition Graphics… | New | $1,280 | In stock | 34 min ago | Buy |
| AmazonPNY NVIDIA GeForce RTX 5070 Slim Dual-Fan | New | $1,311 | In stock | 34 min ago | Buy |
| AmazonMSI Gaming RTX 5070 12G Ventus 2X OC White Graphics Card | New | $1,330 | In stock | 34 min ago | Buy |
| AmazonASUS TUF Gaming GeForce RTX 5070 12GB GDDR7 OC Edition Gaming Graphics Card | New | $1,343 | In stock | 34 min ago | Buy |
| AmazonMSI Gaming RTX 5070 12G Ventus 2X OC Graphics Card | New | $1,362 | In stock | 34 min ago | Buy |
| eBayASUS Prime GeForce RTX 5070 OC 12GB GDDR7 | used, asking price | $1,400 | In stock | 2 h ago | Buy |
| AmazonGIGABYTE GeForce RTX 5070 Eagle OC SFF 12G Graphics Card | New | $1,440 | In stock | 29 min ago | Buy |
| AmazonASUS ROG Strix GeForce RTX 5070 12GB GDDR7 OC Edition Graphics Card | New | $1,450 | In stock | 34 min ago | Buy |
| AmazonMSI GeForce RTX 5070 12G Shadow 2X OC Extreme Performance Graphics Card: 2557MHz | New | $1,469 | In stock | 29 min ago | Buy |
| AmazonZOTAC Gaming GeForce RTX 5070 AMP White Edition DLSS 4 12GB GDDR7 192-bit 28… | New | $1,481 | In stock | 29 min ago | Buy |
| AmazonZOTAC Gaming GeForce RTX 5070 Solid OC DLSS 4 12GB GDDR7 192-bit 28 Gbps PCIE… | New | $1,636 | In stock | 29 min 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 @32k | Prefill | Good for |
|---|---|---|---|---|---|---|---|
| Gemma 4 12B | Q6_K | fits | 10.8 GB | 59k100k with q8 cache | 39tok/sest. | 1044 tok/s | chat, coding, long documents |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 10.8 GB | 47k79k with q8 cache | 39tok/sest. | 1301 tok/s | chat, coding |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q5_K_M | fits | 10.8 GB | 35k65k with q8 cache | 39tok/sest. | 1071 tok/s | chat, coding |
| Qwen3 8B Alibaba Qwen | Q5_K_M | fits | 10.8 GB | 35k40k with q8 cache | 39tok/sest. | 1071 tok/s | chat, coding |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 6.1 GB | 174k256k with q8 cache | 74tok/sest. | 2433 tok/s | chat, coding, long documents |
| Ministral 3 8B Mistral AI | Q5_K_M | fits | 10.8 GB | 36k66k with q8 cache | 39tok/sest. | 1035 tok/s | chat, coding |
| Granite 4.2 8B IBM | Q4_K_M | fits | 11.0 GB | 34k62k with q8 cache | 38tok/sest. | 985 tok/s | chat, coding, agents |
| Gemma 4 E4B | Q8_0 | fits | 9.4 GB | 91k128k with q8 cache | 45tok/sest. | 1634 tok/s | chat, coding, long documents |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 10.8 GB | 43k75k with q8 cache | 94tok/sest. | 5344 tok/s | chat, coding |
| Llama 3.1 8B Meta | Q6_K | fits | 11.0 GB | 34k63k with q8 cache | 38tok/sest. | 1132 tok/s | chat, coding |
| Qwen2.5 0.5B Alibaba Qwen | Q8_0 | fits | 1.8 GB | 32k | 446tok/sest. | 11638 tok/s | chat, coding, long documents |
| Qwen3.5 0.8B Alibaba Qwen | Q8_0 | fits | 2.0 GB | 256k | 338tok/sest. | 10932 tok/s | chat, coding, agents, long documents |
| Qwen3.5 2B Alibaba Qwen | Q5_K_M | fits | 2.6 GB | 256k | 224tok/sest. | 5212 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 1.5B DeepSeek | Q8_0 | fits | 3.5 GB | 128k | 147tok/sest. | 4378 tok/s | chat, coding, long documents |
| MiniCPM5 2B openbmb | Q8_0 | fits | 4.7 GB | 128k | 102tok/sest. | 2615 tok/s | chat, coding, agents, long documents |
| LFM2.5 2.6B Liquid AI | Q8_0 | fits | 5.4 GB | 124k128k with q8 cache | 85tok/sest. | 2962 tok/s | chat, coding, agents, long documents |
| LFM2.5 VL 3B Liquid AI | Q8_0 | fits | 5.4 GB | 32k | 85tok/sest. | 2716 tok/s | chat, coding, agents, long documents |
| granite vision 4.1 4b IBM | Q8_0 | fits | 6.8 GB | 87k128k with q8 cache | 66tok/sest. | 1897 tok/s | chat, coding |
| granite 4.2 3b IBM | Q8_0 | fits | 7.0 GB | 84k128k with q8 cache | 63tok/sest. | 1989 tok/s | chat, coding, agents |
| GLM 4.6V Flash Z.ai | Q4_K_M | fits | 7.9 GB | 110k128k with q8 cache | 56tok/sest. | 891 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 7B DeepSeek | Q8_0 | fits | 10.2 GB | 52k90k with q8 cache | 42tok/sest. | 1279 tok/s | chat, coding |
| Ministral 3 8B Reasoning 2512 Mistral AI | Q5_K_M | fits | 10.8 GB | 36k66k with q8 cache | 39tok/sest. | 1035 tok/s | chat, coding, agents |
| DeepSeek R1 Distill Llama 8B DeepSeek | Q6_K | fits | 11.0 GB | 34k63k with q8 cache | 38tok/sest. | 1132 tok/s | chat, coding |
| Qwen 3.8 27B Alibaba Qwen | UD-Q4_K_M | offload | 18.4 GB | – | 6tok/sest. | 342 tok/s | – |
| Qwen 3.6 27B Alibaba Qwen | Q4_K_M | offload | 18.7 GB | – | 6tok/sest. | 339 tok/s | – |
| Gemma 4 31B | Q4_K_M | offload | 21.2 GB | – | 5tok/sest. | 285 tok/s | – |
| Qwen 3.6 35B-A3B Alibaba Qwen | MXFP4 | offload | 21.8 GB | – | 23tok/sest. | 2255 tok/s | chat, coding |
| Qwen 3.5 27B Alibaba Qwen | Q4_K_M | offload | 18.6 GB | – | 6tok/sest. | 340 tok/s | – |
| Gemma 4 26B-A4B | UD-Q4_K_M | offload | 17.5 GB | – | 21tok/sest. | 2229 tok/s | chat, coding |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q4_K_M | offload | 22.1 GB | – | 22tok/sest. | 2242 tok/s | chat, coding |
| GLM 4.7 Flash Z.ai | Q4_K_M | offload | 19.6 GB | – | 13tok/sest. | 1237 tok/s | chat |
| Devstral Small 2 24B Mistral AI | Q4_K_M | offload | 19.2 GB | – | 5tok/sest. | 353 tok/s | – |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | UD-Q6_K_XL | offload | 33.7 GB | – | 13tok/sest. | 2171 tok/s | – |
| gpt-oss 20B OpenAI | Q4_K_M | offload | 12.5 GB | – | 49tok/sest. | 2266 tok/s | chat, coding, agents, long documents |
| Kimi Linear 48B-A3B Moonshot AI | Q4_K_M | offload | 29.2 GB | – | 22tok/sest. | 1725 tok/s | chat, coding, long documents |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q4_K_M | offload | 21.2 GB | – | 12tok/sest. | 1050 tok/s | chat |
| Qwen3 32B Alibaba Qwen | Q4_K_M | offload | 27.3 GB | – | 3tok/sest. | 179 tok/s | – |
| Gemma 3 27B | Q4_K_M | offload | 19.2 GB | – | 6tok/sest. | 356 tok/s | – |
| Mistral Small 3.2 24B Mistral AI | Q4_K_M | offload | 19.2 GB | – | 5tok/sest. | 353 tok/s | – |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q4_K_M | offload | 27.4 GB | – | 3tok/sest. | 205 tok/s | – |
| Ministral 3 14B Mistral AI | Q4_K_M | offload | 13.6 GB | 18k34k with q8 cache | 14tok/sest. | 648 tok/s | chat |
| Qwen3 14B Alibaba Qwen | Q4_K_M | offload | 14.3 GB | 14k26k with q8 cache | 12tok/sest. | 566 tok/s | chat |
| Phi-4 14B Microsoft | Q4_K_M | offload | 15.4 GB | 12k16k with q8 cache | 9tok/sest. | 545 tok/s | chat |
| Mellum2.1 12B A2.5B Thinking JetBrains | Q6_K | offload | 12.0 GB | – | 63tok/sest. | 3727 tok/s | chat, coding, agents, long documents |
| Kimi VL A3B Moonshot AI | mlx-5bit | offload | 12.9 GB | – | 43tok/sest. | 2687 tok/s | chat, coding, agents |
| LFM2.5 24B A2B Liquid AI | Q4_K_M | offload | 17.7 GB | – | 18tok/sest. | 2309 tok/s | chat |
| GLM 4.1V 9B Thinking Z.ai | mlx-8bit | offload | 13.1 GB | – | 16tok/sest. | 816 tok/s | chat |
| DeepSeek R1 Distill Qwen 14B DeepSeek | Q4_K_M | offload | 15.3 GB | 12k22k with q8 cache | 10tok/sest. | 513 tok/s | chat |
| Devstral Small 2507 Mistral AI | Q4_K_M | offload | 19.2 GB | – | 5tok/sest. | 359 tok/s | – |
| Magistral Small 2506 Mistral AI | Q4_K_M | offload | 19.2 GB | – | 5tok/sest. | 359 tok/s | – |
| Magistral Small 2507 Mistral AI | Q4_K_M | offload | 19.2 GB | – | 5tok/sest. | 359 tok/s | – |
| Magistral Small 2509 Mistral AI | Q4_K_M | offload | 19.2 GB | – | 5tok/sest. | 353 tok/s | – |
| granite 4.2 30b IBM | Q4_K_M | offload | 25.7 GB | – | 3tok/sest. | 241 tok/s | – |
| DeepSeek V4 Flash DeepSeek | UD-Q2_K_XL | won't run | 93.8 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 | 75.2 GB | – | – | – | – |
| MiniMax M2.7 MiniMax | UD-Q2_K_XL | won't run | 78.8 GB | – | – | – | – |
| Qwen 3.5 122B-A10B Alibaba Qwen | UD-Q2_K_XL | won't run | 40.7 GB | – | – | – | – |
| Nemotron 3 Super 120B-A12B NVIDIA | UD-Q2_K_XL | won't run | 52.2 GB | – | – | – | – |
| Qwen3 Coder Next Alibaba Qwen | Q4_K_M | won't run | 46.9 GB | – | – | – | – |
| gpt-oss 120B OpenAI | Q4_K_M | won't run | 60.5 GB | – | – | – | – |
| Mistral Small 4 119B Mistral AI | UD-Q2_K_XL | won't run | 39.0 GB | – | – | – | – |
| GLM 4.5 Air Z.ai | Q2_K | won't run | 48.8 GB | – | – | – | – |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q4_K_M | won't run | 46.9 GB | – | – | – | – |
| Llama 3.3 70B Meta | Q4_K_M | won't run | 50.5 GB | – | – | – | – |
| DeepSeek R1 DeepSeek | Q4_K_M | won't run | 379.7 GB | – | – | – | – |
| DeepSeek R1 0528 DeepSeek | Q4_K_M | won't run | 380.2 GB | – | – | – | – |
| DeepSeek R1 Distill Llama 70B DeepSeek | Q4_K_M | won't run | 50.5 GB | – | – | – | – |
| DeepSeek V3 0324 DeepSeek | Q4_K_M | won't run | 379.7 GB | – | – | – | – |
| DeepSeek V3.1 DeepSeek | Q4_K_M | won't run | 380.6 GB | – | – | – | – |
| DeepSeek V3.2 DeepSeek | Q4_K_M | won't run | 380.6 GB | – | – | – | – |
| DeepSeek V4 Flash 0731 DeepSeek | MXFP4 | won't run | 149.2 GB | – | – | – | – |
| DeepSeek V4 Flash Vision Exp DeepSeek | MXFP4 | won't run | 158.0 GB | – | – | – | – |
| Devstral 2 123B Instruct 2512 Mistral AI | Q8_0 | won't run | 135.6 GB | – | – | – | – |
| GLM 4.5V Z.ai | Q4_K_M | won't run | 65.9 GB | – | – | – | – |
| GLM 4.6V Z.ai | Q4_K_M | won't run | 72.2 GB | – | – | – | – |
| GLM 4.7 Z.ai | Q4_K_M | won't run | 214.0 GB | – | – | – | – |
| GLM 5.1 Z.ai | MXFP4 | won't run | 423.6 GB | – | – | – | – |
| GLM 5.2 Z.ai | UD-Q4_K_M | won't run | 437.5 GB | – | – | – | – |
| GLM 5.3 Z.ai | Q8_0 | won't run | 750.0 GB | – | – | – | – |
| Kimi K2 Moonshot AI | Q4_K_M | won't run | 581.2 GB | – | – | – | – |
| Kimi K2 Instruct 0905 Moonshot AI | Q4_K_M | won't run | 581.6 GB | – | – | – | – |
| Kimi K2 Thinking Moonshot AI | Q4_K_M | won't run | 581.6 GB | – | – | – | – |
| Kimi K2.5 Moonshot AI | Q4_K_M | won't run | 581.6 GB | – | – | – | – |
| MiniMax M2 MiniMax | Q4_K_M | won't run | 137.5 GB | – | – | – | – |
| MiniMax M2.1 MiniMax | Q4_K_M | won't run | 137.5 GB | – | – | – | – |
| MiniMax M2.5 MiniMax | MXFP4 | won't run | 123.9 GB | – | – | – | – |
| MiniMax M3 MiniMax | UD-Q4_K_M | won't run | 251.4 GB | – | – | – | – |
| Mistral Medium 3.5 128B Mistral AI | Q4_K_M | won't run | 81.6 GB | – | – | – | – |
Specifications
From the manufacturer's published specifications; sources are linked where we have them.
- GPU
- GeForce RTX 5070
- Memory
- 12 GB GDDR7
- Memory bus
- 192-bit
- Memory bandwidth
- 672 GB/s
- FP16 compute
- 62 TFLOPS
- Software
- CUDA
- Board power
- 250 W
- PCIe generation
- Gen 5
- PCIe lanes
- x16
Compare with
Questions
- How much memory does the NVIDIA GeForce RTX 5070 have for AI models?
- The NVIDIA GeForce RTX 5070 has 12 GB of GDDR7 memory with 672 GB/s of bandwidth, which sets how fast it generates text.
- What is the best model the NVIDIA GeForce RTX 5070 can run locally?
- Gemma 4 12B (Q6_K) fits fully in its memory at 32k context and generates at about 39 tok/s, an estimate from its memory bandwidth. 23 of the 113 models we track fit at that context.
- Can the NVIDIA GeForce RTX 5070 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 5070 and system RAM can hold.
- How much does the NVIDIA GeForce RTX 5070 cost in Canada?
- The best new price for the NVIDIA GeForce RTX 5070 in Canada is $1,181 at Amazon; used, it starts at $1,150 (asking price).
Speeds on this page are for 32k context. See the best hardware for local AI at every budget.