NVIDIA · Ada Lovelace · 48 GB VRAM tier
Best AI Models for NVIDIA L40 (48 GB)
Runs 27–31B and 35B MoE models well; 70B barely fits and is slow (14 tok/s).
48 GB GDDR6864 GB/s181 TFLOPS FP16300 WAda Lovelace 2022
| # | Model | Speed | llmrun Score | Quant · VRAM |
|---|---|---|---|---|
| 1 | Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB · 32.2 t/s | 32.2 tok/s | Q4_K_M · 17.9 GB | |
| 2 | Qwen3.6 27BAlibaba Q4_K_M · 17.9 GB · 32.2 t/s | 32.2 tok/s | Q4_K_M · 17.9 GB | |
| 3 | Gemma 4 31B ITGoogle Q4_K_M · 21.7 GB · 27.5 t/s | 27.5 tok/s | Q4_K_M · 21.7 GB | |
| 4 | Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 153 t/s | 153 tok/s | Q4_K_M · 16.5 GB | |
| 5 | Q4_K_M · 19.3 GB · 184 t/s | 184 tok/s | Q4_K_M · 19.3 GB |
| # | Model | Speed | Coding Score | Quant · VRAM |
|---|---|---|---|---|
| 1 | Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB · 32.2 t/s | 32.2 tok/s | Q4_K_M · 17.9 GB | |
| 2 | Gemma 4 31B ITGoogle Q4_K_M · 21.7 GB · 27.5 t/s | 27.5 tok/s | Q4_K_M · 21.7 GB | |
| 3 | Qwen3.6 35B A3BAlibaba Q4_K_M · 22.0 GB · 136 t/s | 136 tok/s | Q4_K_M · 22.0 GB | |
| 4 | Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 153 t/s | 153 tok/s | Q4_K_M · 16.5 GB | |
| 5 | Q4_K_M · 19.3 GB · 184 t/s | 184 tok/s | Q4_K_M · 19.3 GB |
| # | Model | Speed | Reasoning Score | Quant · VRAM |
|---|---|---|---|---|
| 1 | Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB · 32.2 t/s | 32.2 tok/s | Q4_K_M · 17.9 GB | |
| 2 | Gemma 4 31B ITGoogle Q4_K_M · 21.7 GB · 27.5 t/s | 27.5 tok/s | Q4_K_M · 21.7 GB | |
| 3 | Qwen3.5 27BAlibaba Q4_K_M · 17.9 GB · 32.2 t/s | 32.2 tok/s | Q4_K_M · 17.9 GB | |
| 4 | Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 153 t/s | 153 tok/s | Q4_K_M · 16.5 GB | |
| 5 | Q4_K_M · 19.3 GB · 184 t/s | 184 tok/s | Q4_K_M · 19.3 GB |
| # | Model | Speed | Math Score | Quant · VRAM |
|---|---|---|---|---|
| 1 | Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB · 32.2 t/s | 32.2 tok/s | Q4_K_M · 17.9 GB | |
| 2 | Qwen3.6 27BAlibaba Q4_K_M · 17.9 GB · 32.2 t/s | 32.2 tok/s | Q4_K_M · 17.9 GB | |
| 3 | Qwen3.6 35B A3BAlibaba Q4_K_M · 22.0 GB · 136 t/s | 136 tok/s | Q4_K_M · 22.0 GB | |
| 4 | Gemma 4 31B ITGoogle Q4_K_M · 21.7 GB · 27.5 t/s | 27.5 tok/s | overall | Q4_K_M · 21.7 GB |
| 5 | Q4_K_M · 19.3 GB · 184 t/s | 184 tok/s | Q4_K_M · 19.3 GB |
| # | Model | Speed ↓ | llmrun Score | Quant · VRAM |
|---|---|---|---|---|
| 1 | Qwen3.5 4BAlibabaHow to run → Q4_K_M · 3.4 GB · 172 t/s | 172 tok/s | Q4_K_M · 3.4 GB | |
| 2 | Q4_K_M · 19.3 GB · 184 t/s | 184 tok/s | Q4_K_M · 19.3 GB | |
| 3 | GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 169 t/s | 169 tok/s | Q4_K_M · 13.1 GB | |
| 4 | Qwen3 30B A3B Thinking 2507Alibaba Q4_K_M · 19.4 GB · 159 t/s | 159 tok/s | Q4_K_M · 19.4 GB | |
| 5 | Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 153 t/s | 153 tok/s | Q4_K_M · 16.5 GB |
| # | Model | Speed | Vision Score | Quant · VRAM |
|---|---|---|---|---|
| 1 | Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB · 32.2 t/s | 32.2 tok/s | Q4_K_M · 17.9 GB | |
| 2 | Qwen3.6 27BAlibaba Q4_K_M · 17.9 GB · 32.2 t/s | 32.2 tok/s | Q4_K_M · 17.9 GB | |
| 3 | Gemma 4 31B ITGoogle Q4_K_M · 21.7 GB · 27.5 t/s | 27.5 tok/s | Q4_K_M · 21.7 GB | |
| 4 | Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 153 t/s | 153 tok/s | Q4_K_M · 16.5 GB | |
| 5 | MiniCPM V 4.7 35B A3BOpenBMB Q4_K_M · 22.1 GB · 153 t/s | 153 tok/s | Q4_K_M · 22.1 GB |
See all 368 models on the L40 →Best quant that fits · speeds estimated on this card
The L40 runs 27–31B and 35B MoE models well. Ada Lovelace generation, released 2022.
GenerationAda Lovelacereleased 2022
L40 strengths and weaknesses
Strengths
- Runs 35B MoE models: Qwen3.6 35B A3B at 136 tok/s in 22 GB
- Room for long context: Qwen3.8 27B at Q4 uses 17.9 GB, leaving 30.1 GB free
Weaknesses
- 120B MoE models don't fit: GPT OSS 120B needs 70.8 GB at Q4 vs 48 GB here
Output speed depends on memory bandwidth (864 GB/s). Grey rows need more than 48 GB.
- 9BQwen3.5 9B · Q4_K_M · 6.6 GB88.3tok/s
- 14BQwen3 14B · Q4_K_M · 11.9 GB59.1tok/s
- 27–31BQwen3.8 27B · Q4_K_M · 17.9 GB32.2tok/s
- 35B MoEQwen3.6 35B A3B · Q4_K_M · 22.0 GB136tok/s
- 13.5tok/s
- 120B MoEGPT OSS 120B · not at 4-bitneeds 70.8 GB
Estimated speeds: Q4_K_M, 4K context, one user. How we estimate
All 1216 models on the L40
Featured onlyBest quant that fits, ordered by llmrun Score. Fit grades how well it runs here, S best. How ranking works
| Model | Quant | VRAM | Speed | Context | Score | Fit |
|---|---|---|---|---|---|---|
HumanizerChat | Q4_K_M | 9.0 GB | 68.2 t/s | 262K | S85, Runs great | |
JiRackUltra 1BChatFunctions | Q4_K_M | 1.8 GB | 395.5 t/s | 131K | S100, Runs great | |
Ling 3.0 TinyChatFunctions | Q4_K_M | 5.5 GB | 335.1 t/s | 131K | S100, Runs great | |
WeVisOne VL 4BVisionFunctions | Q4_K_M | 4.7 GB | 165.7 t/s | 262K | S98, Runs great | |
MiniCPM V 4.6 ThinkingVisionFunctions | Q4_K_M | 1.5 GB | 497.0 t/s | 262K | S100, Runs great | |
Qwen3.5 35B A3BVision | Q4_K_M | 22.0 GB | 135.9 t/s | 262K | S96, Runs great | |
| Q4_K_M | 18.1 GB | 37.1 t/s | 131K | A74, Runs well | ||
MiniCPM O 4 5ChatFunctions | Q4_K_M | 8.3 GB | 90.1 t/s | 41K | S90, Runs great | |
| Q4_K_M | 16.9 GB | 33.9 t/s | 262K | A73, Runs well | ||
OTel 2.0 LLM 31B ITChatFunctions | Q4_K_M | 21.7 GB | 27.5 t/s | 262K | A68, Runs well | |
Hy MT2 30B A3BTranslationFunctions | Q4_K_M | 19.1 GB | 156.0 t/s | 262K | S97, Runs great | |
Llm Jp 4.1 32B A3b ThinkingChatFunctions | Q4_K_M | 20.1 GB | 168.7 t/s | 66K | S98, Runs great | |
DeepSeek R1 Distill Qwen 32BChatReasoningFunctions | Q4_K_M | 24.3 GB | 27.4 t/s | 131K | A68, Runs well | |
Cosmos Reason2 2BVisionChatReasoningFunctions | Q4_K_M | 3.5 GB | 348.8 t/s | — | S100, Runs great | |
Diffusiongemma 26B A4B ITVisionFunctions | Q4_K_M | 16.5 GB | 152.4 t/s | 262K | S97, Runs great |
Specs
- Architecture
- Ada Lovelace
- VRAM
- 48 GB GDDR6
- Memory bandwidth
- 864.0 GB/s
- FP16 (dense)
- 181.05 TFLOPS
- CUDA cores
- 18,176
- Tensor cores
- 568
- Compute capability
- 8.9
- TDP
- 300 W
- Released
- 2022-10-13
L40 FAQ
What is the largest model the L40 can run?
Qwen2.5 72B Instruct (72.7B) is the largest at 4-bit or better: at Q4_K_S it uses 46.6 GB of 48 GB, and runs at about 13.4 tok/s.
Can the L40 run Qwen3.8 27B?
Yes. Qwen3.8 27B fits at Q4_K_M, using 17.9 GB of 48 GB, and it is the best model that runs well on this card.
Can the L40 run 120B MoE models?
No. GPT OSS 120B needs 70.8 GB at Q4, more than the 48 GB on this card.
How many tokens per second does the L40 give?
About 32.2 tok/s on Qwen3.8 27B at Q4_K_M, with the first token after 2.8 s on a 4K-token prompt.
What power supply does the L40 need?
Plan a 600 W PSU (2× the 300 W TDP).
Is 48 GB enough for coding and agents?
Yes for coding: Qwen3.8 27B, the best of the 10 coding models that fit, runs at about 32 tok/s. For agents, not yet: no agent-scored model fits in less than 96 GB.