NVIDIA GeForce RTX 4070 Ti 16 GB
Live eBay prices, cheapest first. The best one right now is $1,195 (new).
Other sizes: 12 GB
Specs
- VRAM
- 16 GB GDDR6X
- Bandwidth
- 504 GB/s
- FP32
- 40.1 TFLOPS
- FP16
- 80 TFLOPS
- Power
- 285 W
- Connector
- PCIe 4.0
- Released
- 2023
- Launch price
- $799.00
- CUDA compute
- 8.9
- Llama 3.1 8B at Q4 (est.)
- 52–78 tokens/s
Price right now
Live on eBayFrom the live listings below; shipping included.
Listings
Live on eBay| Listing | Condition | Price | Checked |
|---|---|---|---|
| New | $1,195or best offerfree shipping | ||
| New | $1,497or best offerfree shipping |
Auctions ending soon
No auctions ending soon right now.
Prices include shipping and were read from eBay at the time shown. They can change: check the listing before you buy.
Owner reviews
No owner reviews yet. Own one? Tell others how it runs.
From signed-in owners, checked before they're published. PerGB doesn't pay for or edit reviews.
How it compares
Live on eBay- Software: CUDA 11.8 and newer.
As much VRAM, about as fast, for less
- NVIDIA Tesla V100 PCIe 16 GB: $325.00, 123% of the GeForce RTX 3090, 16 GB
- Intel Arc A770 16 GB: $431.00, 108% of the GeForce RTX 3090, 16 GB
- NVIDIA Quadro RTX 5000: $449.99, 77% of the GeForce RTX 3090, 16 GB
Faster, for the least
- Intel Arc A770 8 GB: $259.99, 103% of the GeForce RTX 3090, 8 GB
- NVIDIA Tesla V100 PCIe 12 GB: $261.00, 123% of the GeForce RTX 3090, 12 GB
- NVIDIA Titan V: $394.04, 104% of the GeForce RTX 3090, 12 GB
More VRAM, for not much more
- NVIDIA Tesla P40: $270.00, 35% of the GeForce RTX 3090, 24 GB
- NVIDIA GeForce RTX 3080 20 GB: $597.36, 91% of the GeForce RTX 3090, 20 GB
- AMD Instinct MI50 32 GB: $633.68, 64% of the GeForce RTX 3090, 32 GB
From the live listings of every GPU, shipping included; performance against the GeForce RTX 3090 (FP16 or FP32 compute and memory bandwidth). Updated with every build.
Local AI: what it runs
| Model (Q4, 8K context) | GeForce RTX 4070 Ti 16 GB needed | Costs now | Speed (est.) |
|---|---|---|---|
| Llama 3.1 8B | 1 card | $1,195 | 52–78 tokens/s |
| Qwen3 14B | 1 card | $1,195 | 28–42 tokens/s |
| gpt-oss 20B | 1 card | $1,195 | 69–104 tokens/s |
| Gemma 3 27B | 2 cards | $2,692 | 15–23 tokens/s |
| Qwen3 32B | 2 cards | $2,692 | 13–19 tokens/s |
| Llama 3.3 70B | 4 cards | not enough listings | 5.9–8.8 tokens/s |
| gpt-oss 120B | 5 cards | not enough listings | 49–73 tokens/s |
| Qwen3 235B-A22B | more than 8 | — | — |
| DeepSeek R1 / V3 671B | more than 8 | — | — |
Cost: that many of the cheapest live listings. Speed: an estimate from the memory bandwidth for one person chatting. Try other models, sizes and contexts.
Decision models
| Model (Q4, 8K context) | GeForce RTX 4070 Ti 16 GB needed | Costs now | Per question (est.) |
|---|---|---|---|
| Julia-10.144B | 1 card | $1,195 | 9.9–21 ms |
| Laya0.421B | 1 card | $1,195 | 16–35 ms |
| Kev-4B4B | 1 card | $1,195 | 40–85 ms |
| lev4B | 1 card | $1,195 | 119–255 ms |
| OpenJev27B | 2 cards | $2,692 | 142–304 ms |
| Clef27B | 2 cards | $2,692 | 142–304 ms |
| Perplexity Decider v1.227B | 2 cards | $2,692 | 142–304 ms |
| mammoth-127B | 2 cards | $2,692 | 142–304 ms |
Decision models score the options you give them instead of writing text, so they're timed per question. The time is scaled from each model's reported speed on an RTX PRO 6000 by this card's compute and memory bandwidth, within about half either way. About the models.
Compare elsewhere
Search other shops for NVIDIA GeForce RTX 4070 Ti 16 GB. These open the shop's own search; we don't show their prices here.

