NVIDIA L40
Live eBay prices, cheapest first. The best one right now is $6,200 (used).
Specs
- VRAM
- 48 GB GDDR6
- Bandwidth
- 864 GB/s
- FP32
- 90.5 TFLOPS
- FP16
- 181 TFLOPS
- Power
- 300 W
- Connector
- PCIe 4.0
- Released
- 2022
- Launch price
- $7,500 (est.)
- CUDA compute
- 8.9
- Llama 3.1 8B at Q4 (est.)
- 89–134 tokens/s
Running it at home
- Cooling
- Passive: it has no fan. In a desktop it needs air pushed through it, front to back: a fan shroud on its end (3D-printed ones with a 40 mm blower or a 92 mm fan are sold for most of these cards) or a server chassis. Without one it overheats within minutes under load.
- Power
- One 16-pin (12VHPWR / 12V-2x6) power input. Rated 300 W: allow that for each card on top of the rest of the PC.
- Size
- Full height, two slots.
- Motherboard
- Turn on "Above 4G decoding" in the BIOS: without it many boards won't start with a card with this much memory.
A server card: made for a rack server's airflow and power. With these sorted it works in a normal PC.
Price right now
Live on eBayFrom the live listings below; shipping included.
Listings
Live on eBay| Listing | Condition | Price | Checked |
|---|---|---|---|
| Used | $6,200or best offerfree shipping | ||
| Used | $6,799or best offer−41%free shipping | ||
| Used | $6,799or best offer−41%free shipping | ||
| Used | $6,799or best offer−41%free shipping | ||
| Open box | $7,450−35%free shipping | ||
| Open box | $7,499or best offer−35%free shipping | ||
| New | $7,698or best offer−33%free shipping | ||
| New | $8,087−30%+$378.42 shipping | ||
| Used | $8,500or best offer−26%free shipping | ||
| Open box | $8,644or best offer−25%free shipping | ||
| Open box | $8,647or best offer−25%free shipping | ||
| New | $8,719or best offer−24%free shipping | ||
| Open box | $9,000or best offer−22%free shipping | ||
| New | $9,010−22%+$15.00 shipping | ||
| Open box | $11,034or best offerfree shipping | ||
| New | $11,200or best offerfree shipping | ||
| New | $11,800or best offerfree shipping | ||
| New | $11,800or best offerfree shipping | ||
| New | $11,800or best offerfree shipping | ||
| New | $11,800or best offerfree shipping | ||
| New | $11,800or best offerfree shipping | ||
| New | $11,800or best offerfree shipping | ||
| New | $11,800or best offerfree shipping | ||
| New | $11,800or best offerfree shipping | ||
| New | $12,100or best offerfree shipping | ||
| New | $12,100or best offerfree shipping | ||
| New | $12,100or best offerfree shipping | ||
| New | $12,100or best offerfree shipping | ||
| New | $12,345or best offerfree shipping | ||
| New | $12,395or best offerfree shipping | ||
| New | $12,449or best offer+$50.00 shipping | ||
| New | $13,205or 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- #16 of 19 PCIe GPUs with 48 GB or more for the money: $4,042 per GeForce RTX 3090 of performance.
- Software: CUDA 11.8 and newer.
As much VRAM, about as fast, for less
- AMD Instinct MI210: $3,799, 211% of the GeForce RTX 3090, 64 GB
- NVIDIA GeForce RTX 4090 D 48 GB: $5,000, 149% of the GeForce RTX 3090, 48 GB
- NVIDIA GeForce RTX 4090 48 GB: $5,469, 158% of the GeForce RTX 3090, 48 GB
Faster, for the least
- AMD Instinct MI100: $1,240, 185% of the GeForce RTX 3090, 32 GB
- NVIDIA GeForce RTX 5090: $5,000, 237% of the GeForce RTX 3090, 32 GB
- NVIDIA A100 PCIe 40 GB: $5,588, 270% of the GeForce RTX 3090, 40 GB
More VRAM, for not much more
- NVIDIA A16: $2,200, 93% of the GeForce RTX 3090, 64 GB
- AMD Instinct MI210: $3,799, 211% of the GeForce RTX 3090, 64 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) | L40 needed | Costs now | Speed (est.) |
|---|---|---|---|
| Llama 3.1 8B | 1 card | $6,200 | 89–134 tokens/s |
| Qwen3 14B | 1 card | $6,200 | 48–72 tokens/s |
| gpt-oss 20B | 1 card | $6,200 | 119–178 tokens/s |
| Gemma 3 27B | 1 card | $6,200 | 26–39 tokens/s |
| Qwen3 32B | 1 card | $6,200 | 22–33 tokens/s |
| Llama 3.3 70B | 1 card | $6,200 | 10–15 tokens/s |
| gpt-oss 120B | 2 cards | $12,999 | 84–126 tokens/s |
| Qwen3 235B-A22B | 4 cards | $26,597 | 19–29 tokens/s |
| 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) | L40 needed | Costs now | Per question (est.) |
|---|---|---|---|
| Julia-10.144B | 1 card | $6,200 | 5.0–11 ms |
| Laya0.421B | 1 card | $6,200 | 8.4–18 ms |
| Kev-4B4B | 1 card | $6,200 | 20–43 ms |
| lev4B | 1 card | $6,200 | 60–129 ms |
| OpenJev27B | 1 card | $6,200 | 72–154 ms |
| Clef27B | 1 card | $6,200 | 72–154 ms |
| Perplexity Decider v1.227B | 1 card | $6,200 | 72–154 ms |
| mammoth-127B | 1 card | $6,200 | 72–154 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 L40. These open the shop's own search; we don't show their prices here.































