NVIDIA GeForce RTX 4070 Ti Super
16 GB · 672 GB/s · 285 W
Prices
Every retailer we track in the US, cheapest first. Buy links may earn us a commission.
| Retailer | Condition | Price | Stock | Checked | Buy |
|---|---|---|---|---|---|
| AmazonASUS TUF Gaming GeForce RTX 4070 Ti Super BTF White OC Edition Gaming Graphics… | New | $1,013 | In stock | 18 min ago | Buy |
| AmazonGIGABYTE GeForce RTX 4070 Ti Super Gaming OC 16G Graphics Card | New | $1,140 | In stock | 18 min ago | Buy |
| AmazonASUS TUF Gaming GeForce RTX 4070 Ti Super BTF White OC Edition Gaming Graphics… | New | $1,170 | In stock | 18 min ago | Buy |
| AmazonASUS TUF Gaming GeForce RTX 4070 Ti Super 16GB GDDR6X OC Edition Gaming… | New | $1,180 | In stock | 18 min ago | Buy |
| AmazonMSI Gaming RTX 4070 TI Super 16G Ventus 3X OC Graphics Card | refurbished | $1,330 | In stock | 18 min ago | Buy |
| AmazonMSI Gaming RTX 4070 Ti Super 16G Ventus 2X OC Graphics Card | refurbished | $1,330 | In stock | 18 min ago | Buy |
| AmazonGIGABYTE GeForce RTX 4070 Ti Super WINDFORCE OC 16G Graphics Card | refurbished | $1,330 | In stock | 17 min ago | Buy |
| AmazonGIGABYTE GeForce RTX 4070 Ti Super Eagle OC 16G Graphics Card | New | $1,400 | In stock | 18 min ago | Buy |
| AmazonMSI Gaming RTX 4070 Ti Super 16G Gaming X Slim Graphics Card | New | $1,435 | In stock | 18 min ago | Buy |
| AmazonGigabyte GeForce RTX 4070 Ti Super WINDFORCE OC Graphics Card | New | $1,455 | In stock | 18 min ago | Buy |
| AmazonZOTAC GAMING GeForce RTX 4070 Ti SUPER Trinity Black Edition 16GB GDDR6X | New | $1,459 | In stock | 18 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 | 36k64k with q8 cache | 14tok/sest. | 693 tok/s | – |
| Qwen 3.6 27B Alibaba Qwen | Q8_0 | fits | 28.4 GB | 42k74k with q8 cache | 14tok/sest. | 693 tok/s | – |
| Gemma 4 31B | Q6_K | fits | 26.0 GB | 64k122k with q8 cache | 16tok/sest. | 604 tok/s | chat |
| Qwen 3.6 35B-A3B Alibaba Qwen | UD-Q6_K | fits | 28.7 GB | 92k144k with q8 cache | 93tok/sest. | 5936 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 27B Alibaba Qwen | Q8_0 | fits | 28.4 GB | 42k74k with q8 cache | 14tok/sest. | 693 tok/s | – |
| Gemma 4 26B-A4B | Q8_0 | fits | 26.5 GB | 176k256k with q8 cache | 55tok/sest. | 4523 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q6_K | fits | 28.2 GB | 109k170k with q8 cache | 95tok/sest. | 5936 tok/s | chat, coding, agents, long documents |
| GLM 4.7 Flash Z.ai | Q6_K | fits | 24.6 GB | 116k198k with q8 cache | 55tok/sest. | 3322 tok/s | chat, coding, agents, long documents |
| Devstral Small 2 24B Mistral AI | Q8_0 | fits | 25.7 GB | 39k71k with q8 cache | 16tok/sest. | 781 tok/s | chat |
| Kimi Linear 48B-A3B Moonshot AI | Q4_K_M | fits | 29.2 GB | 122k167k with q8 cache | 129tok/sest. | 5642 tok/s | chat, coding, long documents |
| gpt-oss 20B OpenAI | MXFP4 | fits | 12.6 GB | 128k | 95tok/sest. | 4296 tok/s | chat, coding, agents, long documents |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q6_K | fits | 25.3 GB | 63k113k with q8 cache | 76tok/sest. | 4294 tok/s | chat, coding, agents |
| Qwen3 32B Alibaba Qwen | Q6_K | fits | 28.2 GB | 18k33k with q8 cache | 14tok/sest. | 534 tok/s | – |
| Gemma 4 12B | Q8_0 | fits | 13.4 GB | 256k | 32tok/sest. | 1576 tok/s | chat, coding, long documents |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 10.3 GB | 256k | 42tok/sest. | 1996 tok/s | chat, coding, long documents |
| Mistral Small 3.2 24B Mistral AI | Q8_0 | fits | 25.7 GB | 39k71k with q8 cache | 16tok/sest. | 781 tok/s | chat |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q6_K | fits | 28.2 GB | 18k33k with q8 cache | 14tok/sest. | 559 tok/s | – |
| Gemma 3 27B | Q8_0 | fits | 28.9 GB | 30k58k with q8 cache | 14tok/sest. | 702 tok/s | – |
| Ministral 3 14B Mistral AI | Q8_0 | fits | 15.8 GB | 100k183k with q8 cache | 27tok/sest. | 1295 tok/s | chat, coding |
| Qwen3 14B Alibaba Qwen | Q8_0 | fits | 17.0 GB | 40k | 24tok/sest. | 1204 tok/s | chat |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q8_0 | fits | 10.4 GB | 128k | 42tok/sest. | 2107 tok/s | chat, coding |
| Qwen3 8B Alibaba Qwen | Q8_0 | fits | 10.4 GB | 40k | 42tok/sest. | 2107 tok/s | chat, coding |
| Phi-4 14B Microsoft | Q8_0 | fits | 17.2 GB | 16k | 24tok/sest. | 1212 tok/s | chat |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 5.6 GB | 256k | 87tok/sest. | 4018 tok/s | chat, coding, long documents |
| Ministral 3 8B Mistral AI | Q8_0 | fits | 10.6 GB | 153k256k with q8 cache | 41tok/sest. | 1968 tok/s | chat, coding, long documents |
| Granite 4.2 8B IBM | Q8_0 | fits | 11.1 GB | 128k | 39tok/sest. | 1954 tok/s | chat, coding |
| Gemma 4 E4B | Q8_0 | fits | 9.0 GB | 128k | 49tok/sest. | 2419 tok/s | chat, coding, long documents |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 9.9 GB | 125k | 170tok/sest. | 14116 tok/s | chat, coding, long documents |
| Llama 3.1 8B Meta | Q6_K | fits | 8.3 GB | 128k | 54tok/sest. | 2175 tok/s | chat, coding, long documents |
| Qwen 3.5 122B-A10B Alibaba Qwen | UD-Q2_K_XL | offload | 40.4 GB | – | 25tok/sest. | 1563 tok/s | chat, coding |
| Qwen3 Coder Next Alibaba Qwen | Q4_K_M | offload | 46.6 GB | – | 28tok/sest. | 3663 tok/s | chat, coding |
| Nemotron 3 Super 120B-A12B NVIDIA | UD-Q2_K_XL | offload | 52.3 GB | – | 12tok/sest. | 1207 tok/s | – |
| Mistral Small 4 119B Mistral AI | UD-Q2_K_XL | offload | 38.8 GB | – | 40tok/sest. | 2090 tok/s | chat, coding, agents, long documents |
| GLM 4.5 Air Z.ai | Q2_K | offload | 44.8 GB | – | 9tok/sest. | 738 tok/s | – |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q4_K_M | offload | 46.6 GB | – | 36tok/sest. | 4606 tok/s | chat, coding |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | UD-Q6_K_XL | offload | 33.8 GB | – | 45tok/sest. | 5840 tok/s | chat, coding, agents, long documents |
| Llama 3.3 70B Meta | Q4_K_M | offload | 43.2 GB | – | 3tok/sest. | 215 tok/s | – |
| 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 | – | – | – | – |
| gpt-oss 120B OpenAI | MXFP4 | won't run | 60.5 GB | – | – | – | – |
Specifications
From the manufacturer's published specifications; sources are linked where we have them.
- GPU
- GeForce RTX 4070 Ti Super
- Memory
- 16 GB GDDR6X
- Memory bus
- 256-bit
- Memory bandwidth
- 672 GB/s
- FP16 compute
- 88 TFLOPS
- Software
- CUDA
- Board power
- 285 W
- PCIe generation
- Gen 4
- PCIe lanes
- x16