aliteq.

L40 48GB, what it runs and what it costs to rent

Specs checked · Rental prices from · Aliteq Team · How we compute this

Some links on this page are referral links: we may earn a commission, at no cost to you.

The short answer

The NVIDIA L40 has 48 GB of VRAM and 864 GB/s of memory bandwidth (2022). At Q4_K_M quality or better with an 8K context it runs 43 of the open models we track; the largest that fits with room to spare is Llama 3.3 70B Instruct. The cheapest rental right now is $0.347/hr (Vast.ai, interruptible).

VRAM
48 GB
Bandwidth
864 GB/s
Board power
300 W
Launched
2022

Source: NVIDIA specification · bandwidth not yet confirmed by a second source, so we don't estimate speed from it

Rent the L40

ProviderTypeFrom, per hourRent
Vast.aiSpot (can be interrupted)$0.347/hrVast.ai
Vast.aiOn demand$0.364/hrVast.ai
RunpodOn demand$0.820/hrRunpod

Lowest price per provider in our hourly snapshot (). Rent buttons are referral links. Every card side by side: cloud GPU prices.

Before you rent the L40: Runpod vs Vast.ai vs Lambda · is Vast.ai safe · is Runpod worth it · rent or buy · every AI GPU's buy and rent price.

L40 rental price history

The cheapest L40 offer we saw each day on the providers we track, since Aug 20. Renting it on demand costs $0.364/hr now; the lowest since Nov 2 was $0.201/hr on Nov 8 (Vast.ai), so today is 82% above that.

On demand now
$0.364/hr
Lowest on demand since Nov 2
$0.201/hr · Nov 8
Cheapest offer now
$0.347/hr
Lowest offer since Aug 20
$0.133/hr · Nov 7
  • Cheapest offer, incl. interruptible
  • Cheapest on demand (from Nov 2)
$0$0.25$0.50$0.75Aug 20Oct 4nowlowest offer $0.133/hrAug 20: cheapest $0.690/hr on RunpodAug 21: cheapest $0.690/hr on RunpodAug 22: cheapest $0.690/hr on RunpodAug 23: cheapest $0.576/hr on Vast.aiAug 24: cheapest $0.402/hr on Vast.aiAug 25: cheapest $0.402/hr on Vast.aiAug 26: cheapest $0.402/hr on Vast.aiAug 27: cheapest $0.335/hr on Vast.aiAug 28: cheapest $0.335/hr on Vast.aiAug 29: cheapest $0.335/hr on Vast.aiAug 30: cheapest $0.335/hr on Vast.aiAug 31: cheapest $0.335/hr on Vast.aiSep 1: cheapest $0.335/hr on Vast.aiSep 2: cheapest $0.335/hr on Vast.aiSep 3: cheapest $0.335/hr on Vast.aiSep 4: cheapest $0.335/hr on Vast.aiSep 5: cheapest $0.335/hr on Vast.aiSep 6: cheapest $0.335/hr on Vast.aiSep 7: cheapest $0.336/hr on Vast.aiSep 8: cheapest $0.336/hr on Vast.aiSep 9: cheapest $0.336/hr on Vast.aiSep 10: cheapest $0.336/hr on Vast.aiSep 11: cheapest $0.336/hr on Vast.aiSep 12: cheapest $0.338/hr on Vast.aiSep 13: cheapest $0.338/hr on Vast.aiSep 14: cheapest $0.336/hr on Vast.aiSep 15: cheapest $0.336/hr on Vast.aiSep 16: cheapest $0.336/hr on Vast.aiSep 17: cheapest $0.338/hr on Vast.aiSep 18: cheapest $0.338/hr on Vast.aiSep 19: cheapest $0.338/hr on Vast.aiSep 20: cheapest $0.338/hr on Vast.aiSep 21: cheapest $0.338/hr on Vast.aiSep 22: cheapest $0.338/hr on Vast.aiSep 23: cheapest $0.336/hr on Vast.aiSep 24: cheapest $0.336/hr on Vast.aiSep 25: cheapest $0.336/hr on Vast.aiSep 26: cheapest $0.336/hr on Vast.aiSep 27: cheapest $0.336/hr on Vast.aiSep 28: cheapest $0.336/hr on Vast.aiSep 29: cheapest $0.338/hr on Vast.aiSep 30: cheapest $0.335/hr on Vast.aiOct 1: cheapest $0.338/hr on Vast.aiOct 2: cheapest $0.338/hr on Vast.aiOct 3: cheapest $0.335/hr on Vast.aiOct 4: cheapest $0.335/hr on Vast.aiOct 5: cheapest $0.335/hr on Vast.aiOct 6: cheapest $0.335/hr on Vast.aiOct 7: cheapest $0.335/hr on Vast.aiOct 8: cheapest $0.335/hr on Vast.aiOct 9: cheapest $0.335/hr on Vast.aiOct 10: cheapest $0.335/hr on Vast.aiOct 11: cheapest $0.335/hr on Vast.aiOct 12: cheapest $0.335/hr on Vast.aiOct 13: cheapest $0.361/hr on Vast.aiOct 14: cheapest $0.361/hr on Vast.aiOct 15: cheapest $0.361/hr on Vast.aiOct 16: cheapest $0.361/hr on Vast.aiOct 17: cheapest $0.361/hr on Vast.aiOct 18: cheapest $0.364/hr on Vast.aiOct 19: cheapest $0.364/hr on Vast.aiOct 20: cheapest $0.364/hr on Vast.aiOct 21: cheapest $0.364/hr on Vast.aiOct 22: cheapest $0.364/hr on Vast.aiOct 23: cheapest $0.334/hr on Vast.aiOct 24: cheapest $0.334/hr on Vast.aiOct 25: cheapest $0.336/hr on Vast.aiOct 26: cheapest $0.334/hr on Vast.aiOct 27: cheapest $0.267/hr on Vast.aiOct 28: cheapest $0.268/hr on Vast.aiOct 29: cheapest $0.330/hr on LiumOct 30: cheapest $0.267/hr on Vast.aiOct 31: cheapest $0.267/hr on Vast.aiNov 1: cheapest $0.267/hr on Vast.aiNov 2: cheapest $0.268/hr on Vast.ai, on demand $0.268/hr on Vast.aiNov 3: cheapest $0.347/hr on Vast.ai, on demand $0.361/hr on Vast.aiNov 4: cheapest $0.347/hr on Vast.ai, on demand $0.361/hr on Vast.aiNov 5: cheapest $0.347/hr on Vast.ai, on demand $0.361/hr on Vast.aiNov 6: cheapest $0.267/hr on Vast.ai, on demand $0.267/hr on Vast.aiNov 7: cheapest $0.133/hr on Vast.ai, on demand $0.202/hr on Vast.aiNov 8: cheapest $0.133/hr on Vast.ai, on demand $0.201/hr on Vast.aiNov 9: cheapest $0.330/hr on Lium, on demand $0.330/hr on LiumNov 10: cheapest $0.347/hr on Vast.ai, on demand $0.361/hr on Vast.aiNov 11: cheapest $0.347/hr on Vast.ai, on demand $0.361/hr on Vast.aiNov 12: cheapest $0.347/hr on Vast.ai, on demand $0.361/hr on Vast.aiNov 13: cheapest $0.347/hr on Vast.ai, on demand $0.361/hr on Vast.aiNov 14: cheapest $0.347/hr on Vast.ai, on demand $0.361/hr on Vast.aiNov 15: cheapest $0.347/hr on Vast.ai, on demand $0.361/hr on Vast.aiNov 16: cheapest $0.347/hr on Vast.ai, on demand $0.361/hr on Vast.aiNov 17: cheapest $0.347/hr on Vast.ai, on demand $0.364/hr on Vast.aiNov 18 (now): cheapest $0.347/hr on Vast.ai, on demand $0.364/hr on Vast.ai

Daily minimum of our hourly readings of Vast.ai, Runpod and Lium. Interruptible (spot) offers can be taken back mid-job. Before Nov 2 Vast mixed spot into on-demand and Runpod listed Community Cloud rates, so the on-demand line starts then. Every number is in our open daily price file.

Every day as a table
DayCheapest offerCheapest on demand
Nov 18 (now)$0.347/hr · Vast.ai$0.364/hr · Vast.ai
Nov 17$0.347/hr · Vast.ai$0.364/hr · Vast.ai
Nov 16$0.347/hr · Vast.ai$0.361/hr · Vast.ai
Nov 15$0.347/hr · Vast.ai$0.361/hr · Vast.ai
Nov 14$0.347/hr · Vast.ai$0.361/hr · Vast.ai
Nov 13$0.347/hr · Vast.ai$0.361/hr · Vast.ai
Nov 12$0.347/hr · Vast.ai$0.361/hr · Vast.ai
Nov 11$0.347/hr · Vast.ai$0.361/hr · Vast.ai
Nov 10$0.347/hr · Vast.ai$0.361/hr · Vast.ai
Nov 9$0.330/hr · Lium$0.330/hr · Lium
Nov 8$0.133/hr · Vast.ai$0.201/hr · Vast.ai
Nov 7$0.133/hr · Vast.ai$0.202/hr · Vast.ai
Nov 6$0.267/hr · Vast.ai$0.267/hr · Vast.ai
Nov 5$0.347/hr · Vast.ai$0.361/hr · Vast.ai
Nov 4$0.347/hr · Vast.ai$0.361/hr · Vast.ai
Nov 3$0.347/hr · Vast.ai$0.361/hr · Vast.ai
Nov 2$0.268/hr · Vast.ai$0.268/hr · Vast.ai
Nov 1$0.267/hr · Vast.ai—
Oct 31$0.267/hr · Vast.ai—
Oct 30$0.267/hr · Vast.ai—
Oct 29$0.330/hr · Lium—
Oct 28$0.268/hr · Vast.ai—
Oct 27$0.267/hr · Vast.ai—
Oct 26$0.334/hr · Vast.ai—
Oct 25$0.336/hr · Vast.ai—
Oct 24$0.334/hr · Vast.ai—
Oct 23$0.334/hr · Vast.ai—
Oct 22$0.364/hr · Vast.ai—
Oct 21$0.364/hr · Vast.ai—
Oct 20$0.364/hr · Vast.ai—
Oct 19$0.364/hr · Vast.ai—
Oct 18$0.364/hr · Vast.ai—
Oct 17$0.361/hr · Vast.ai—
Oct 16$0.361/hr · Vast.ai—
Oct 15$0.361/hr · Vast.ai—
Oct 14$0.361/hr · Vast.ai—
Oct 13$0.361/hr · Vast.ai—
Oct 12$0.335/hr · Vast.ai—
Oct 11$0.335/hr · Vast.ai—
Oct 10$0.335/hr · Vast.ai—
Oct 9$0.335/hr · Vast.ai—
Oct 8$0.335/hr · Vast.ai—
Oct 7$0.335/hr · Vast.ai—
Oct 6$0.335/hr · Vast.ai—
Oct 5$0.335/hr · Vast.ai—
Oct 4$0.335/hr · Vast.ai—
Oct 3$0.335/hr · Vast.ai—
Oct 2$0.338/hr · Vast.ai—
Oct 1$0.338/hr · Vast.ai—
Sep 30$0.335/hr · Vast.ai—
Sep 29$0.338/hr · Vast.ai—
Sep 28$0.336/hr · Vast.ai—
Sep 27$0.336/hr · Vast.ai—
Sep 26$0.336/hr · Vast.ai—
Sep 25$0.336/hr · Vast.ai—
Sep 24$0.336/hr · Vast.ai—
Sep 23$0.336/hr · Vast.ai—
Sep 22$0.338/hr · Vast.ai—
Sep 21$0.338/hr · Vast.ai—
Sep 20$0.338/hr · Vast.ai—
Sep 19$0.338/hr · Vast.ai—
Sep 18$0.338/hr · Vast.ai—
Sep 17$0.338/hr · Vast.ai—
Sep 16$0.336/hr · Vast.ai—
Sep 15$0.336/hr · Vast.ai—
Sep 14$0.336/hr · Vast.ai—
Sep 13$0.338/hr · Vast.ai—
Sep 12$0.338/hr · Vast.ai—
Sep 11$0.336/hr · Vast.ai—
Sep 10$0.336/hr · Vast.ai—
Sep 9$0.336/hr · Vast.ai—
Sep 8$0.336/hr · Vast.ai—
Sep 7$0.336/hr · Vast.ai—
Sep 6$0.335/hr · Vast.ai—
Sep 5$0.335/hr · Vast.ai—
Sep 4$0.335/hr · Vast.ai—
Sep 3$0.335/hr · Vast.ai—
Sep 2$0.335/hr · Vast.ai—
Sep 1$0.335/hr · Vast.ai—
Aug 31$0.335/hr · Vast.ai—
Aug 30$0.335/hr · Vast.ai—
Aug 29$0.335/hr · Vast.ai—
Aug 28$0.335/hr · Vast.ai—
Aug 27$0.335/hr · Vast.ai—
Aug 26$0.402/hr · Vast.ai—
Aug 25$0.402/hr · Vast.ai—
Aug 24$0.402/hr · Vast.ai—
Aug 23$0.576/hr · Vast.ai—
Aug 22$0.690/hr · Runpod—
Aug 21$0.690/hr · Runpod—
Aug 20$0.690/hr · Runpod—

Which AI models run on the L40

Computed by our VRAM engine for an 8K context: the best quality each model fits at in 48 GB. Speeds are upper-bound estimates from memory bandwidth, not benchmarks.

ModelBest fitVRAM used~tok/s
Qwen3-Next 80B-A3B (MoE)Q4_K_M46 GB96% · tight—
Qwen3-Coder-Next 80B-A3B (MoE)Q4_K_M46 GB96% · tight—
Llama 3.3 70B InstructQ4_K_M43 GB90%—
DeepSeek R1 Distill 70BQ4_K_M43 GB90%—
Mixtral 8x7B (MoE)Q8_048 GB100% · tight—
Qwen3.5 35B-A3B (MoE)Q8_037 GB76%—
Qwen3.6 35B-A3B (MoE)Q8_037 GB76%—
Ornith-1.5 35B-A3B (MoE)Q8_037 GB76%—
DeepSeek R1 Distill 32BQ8_035 GB73%—
Qwen2.5 32B InstructQ8_035 GB73%—
Qwen2.5 Coder 32BQ8_035 GB73%—
Qwen3 32BQ8_035 GB73%—

Fits only below Q4 quality: Mistral Small 4 119B (MoE) (Q2_K), Llama 4 Scout 17B-16E (MoE) (Q2_K), GLM-4.5-Air (MoE) (Q2_K).

Too big for 48 GB (rent a bigger card instead): what it costs to run gpt-oss 120B (MoE), what it costs to run NVIDIA Nemotron 3 Super 120B-A12B (MoE), what it costs to run NVIDIA Nemotron 3.5 Super VL 120B-A12B (MoE), what it costs to run Qwen3.5 122B-A10B (MoE).

Check a model and context of your own in the VRAM calculator.

AI video on the L40

Alibaba's Wan 2.2 is an open video model you can run yourself in ComfyUI. With 48 GB the L40 fits:

  • Wan 2.2 14B in fp16, or in fp8 at 720p (48 GB and up, per Runpod's Wan 2.2 guide)
  • Wan 2.2 14B at 640x640 with fp8 weights (24 GB and up, per Runpod's Wan 2.2 guide)
  • Wan 2.2 5B, with ComfyUI's native offloading (8 GB and up, per ComfyUI's Wan 2.2 docs)

What each setup needs, the cheapest card to rent and what one clip costs: cloud GPUs for ComfyUI with Flux and Wan 2.2. Against an app or an API: AI video cost per clip, app vs API vs rented GPU. Which open model to run, and the licence catch for US users: the best open source AI video generator. Picking by job instead (YouTube, TikTok, ads, animation)? See the best AI video generator for each job. Rather not run a model yourself? Hosted video models such as Seedance, Veo and Hailuo are compared in Kling AI alternatives, priced per clip.

Our guides on the L40

Cards to compare it with

Every card by VRAM tier: all GPUs for gaming and local AI.

Common questions about the L40

How much VRAM does the L40 have?
48 GB, with 864 GB/s of memory bandwidth, per the maker's specification.
What is the biggest AI model the L40 can run?
Of the open models we track, Llama 3.3 70B Instruct is the largest that fits at Q4_K_M or better with an 8K context and room to spare (about 43 GB of 48 GB). Qwen3-Next 80B-A3B (MoE) also squeezes in, but with almost no memory left for longer context. Bigger models only fit at lower-quality quants or need more memory.
How much does it cost to rent an L40?
From $0.347/hr on Vast.ai (spot, can be interrupted), the lowest price in our hourly snapshot of Nov 18, 2026. Prices move every hour.
Is 48 GB enough?
Top-end gaming and workstation cards; 70B-class models at low-bit quants.