NVIDIA L40 for local LLMs
Written by Jakub Rusinowski · Last updated
With 48 GB of GDDR6 at 864 GB/s, the L40 runs 115 catalogued models at Q4_K_M with 8K context. The largest that fits is Llama 3.3 70B Instruct (~45.7 GB), and the top pick is Cosmos 3 Super at 23–45 tok/s.
48 GB of GDDR6 with ECC, 864 GB/s, 300 W. Not the L40S, which shares the memory system but has different tensor performance.
Models that run on the L40
Q4_K_M, 8K context, 48 GB usable. Ranked by quality and speed.
| Model | Memory · marker = 48 GB | VRAM | Speed |
|---|---|---|---|
| Cosmos 3 Super Cosmos 3 | 39.4 GB | 23–45 tok/s | |
| Qwen 3.6 35B-A3B Qwen 3.6 | 21.9 GB | 100–192 tok/s | |
| Nex-N2.5 mini Nex-N2.5 | 21.9 GB | 100–192 tok/s | |
| Nex-N2 mini Nex-N2 | 21.9 GB | 100–192 tok/s | |
| Qwen 3.5 35B-A3B Qwen 3.5 | 21.9 GB | 100–192 tok/s | |
| Laguna XS 2.1 33B-A3B Poolside Laguna XS 2.1 | 20.7 GB | 101–193 tok/s | |
| Qwen 3 32B Qwen 3 | 22.8 GB | 23–44 tok/s | |
| Aya Expanse 32B Aya Expanse | 21.6 GB | 24–47 tok/s | |
| EXAONE 3.5 32B EXAONE 3.5 | 22.3 GB | 24–45 tok/s | |
| Cogito v1 32B Cogito v1 | 22.3 GB | 24–45 tok/s | |
| Granite 4.0 Small-H 32B-A9B IBM Granite 4.0 | 20.1 GB | 60–116 tok/s | |
| Olmo 3 32B Olmo 3 | 20.1 GB | 24–46 tok/s |
Buy it or rent the same memory
Buy the card, or rent a GPU with the same memory by the hour to try models first.
As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.
Speed vs other GPUs
Llama 3.1 8B, Q4_K_M. Estimated ranges. How this is calculated
Specifications
Specs last updated 2026-10-07.
- Memory
- 48 GB GDDR6
- Memory bandwidth
- 864 GB/s
- Memory bus
- 384-bit
- Architecture
- Ada Lovelace AD102
- Series
- Data center
- Board power
- 300 W
- Release year
- 2022
- Compute backends
- CUDA
- Usable for models
- 48 GB
Similar GPUs
Frequently asked questions
Can the NVIDIA L40 run local LLMs?
Yes. With 48 GB (48 GB usable by a model) it runs 115 of the catalogued models at Q4_K_M with 8K context; the largest is Llama 3.3 70B Instruct, needing about 45.7 GB.
How fast is the NVIDIA L40 for AI inference?
It is estimated to run Llama 3.1 8B at 77–147 tok/s at Q4_K_M. Llama 3.3 70B is estimated at 12–23 tok/s. These are modelled estimates from memory bandwidth, not measurements; the methodology page shows the formula.
What LLMs can I run on 48 GB?
Among the best that fit: Cosmos 3 Super, Qwen 3.6 35B-A3B, Nex-N2.5 mini, Nex-N2 mini, Qwen 3.5 35B-A3B.