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

What LLMs can the L40 run?

#	Model	Speed	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	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 184 t/s	184 tok/s	Q4_K_M · 19.3 GB

#	Model	Speed	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	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 184 t/s	184 tok/s	Q4_K_M · 19.3 GB

#	Model	Speed	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	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA 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	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 184 t/s	184 tok/s		Q4_K_M · 19.3 GB

#	Model	Speed ↓	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	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA 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	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

About the L40

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

L40 tokens per second by model size

Output speed depends on memory bandwidth (864 GB/s). Grey rows need more than 48 GB.

9BQwen3.5 9B · Q4_K_M · 6.6 GB
88.3tok/s
14BQwen3 14B · Q4_K_M · 11.9 GB
59.1tok/s
27–31BQwen3.8 27B · Q4_K_M · 17.9 GB
32.2tok/s
35B MoEQwen3.6 35B A3B · Q4_K_M · 22.0 GB
136tok/s
70BLlama 3.3 70B Instruct · IQ4_XS · 46.4 GB tight · IQ4_XS
13.5tok/s
120B MoEGPT OSS 120B · not at 4-bit
needs 70.8 GB

Estimated speeds: Q4_K_M, 4K context, one user. How we estimate

All 1216 models on the L40

Featured only

Best quant that fits, ordered by llmrun Score. Fit grades how well it runs here, S best. How ranking works

LLM models compatible with NVIDIA L40 — ranked by Score, recency and Fit
Model	Quant	VRAM	Speed	Context	Fit
LFM2.5 1.2B JP 2026061.2BChat Q4_K_M·524.9 t/s	Q4_K_M	1.2 GB3%	524.9 t/s	128K	S100, Runs great
TLive Omni 4B5.8BChatVisionFunctions BF16·46.4 t/s	BF16	13.3 GB28%	46.4 t/s	262K	A78, Runs well
Qwen2.5 7B Pyuigpt7.6BChatFunctions Q4_K_M·112.5 t/s	Q4_K_M	5.8 GB12%	112.5 t/s	33K	S94, Runs great
GLM 4.7 Flash REAP 23B A3B23.0BChat Q4_K_M·141.3 t/s	Q4_K_M	15.0 GB31%	141.3 t/s	203K	S96, Runs great
GPT OSS 20B NPU220BChatFunctions Q4_K_M·202.8 t/s	Q4_K_M	12.6 GB26%	202.8 t/s	131K	S100, Runs great
OneRec 1.7B2.1BChatFunctions Q4_K_M·310.3 t/s	Q4_K_M	3.5 GB7%	310.3 t/s	41K	S100, Runs great
Darwin 36B Opus34.7BChatReasoningFunctions Q4_K_M·167.8 t/s	Q4_K_M	21.3 GB44%	167.8 t/s	262K	S98, Runs great
Typhoon2.5 Qwen3 30B A3b30.5BChat Q4_K_M·158.7 t/s	Q4_K_M	19.4 GB40%	158.7 t/s	262K	S97, Runs great
DeepSeek OCR3.3BVision Q4_K_M·467.3 t/s	Q4_K_M	2.8 GB6%	467.3 t/s	8K	S100, Runs great
LLaDA2.0 Mini16.3BChatFunctions Q4_K_M·371.5 t/s	Q4_K_M	10.7 GB22%	371.5 t/s	33K	S100, Runs great
Kimi VL A3B Instruct16.4BVisionFunctions Q4_K_M·186.8 t/s	Q4_K_M	10.7 GB22%	186.8 t/s	131K	S99, Runs great
Gemma 4 12B OBLITERATED12.0BChat Q4_K_M·68.2 t/s	Q4_K_M	9.0 GB19%	68.2 t/s	131K	S85, Runs great
Karnak 40B v1.040.7BChat Q4_K_M·119.9 t/s	Q4_K_M	25.8 GB54%	119.9 t/s	262K	S95, Runs great
Qwen3 0.6B752MChatFunctions Q4_K_M·645.5 t/s	Q4_K_M	1.7 GB4%	645.5 t/s	41K	S100, Runs great
LocoOperator 4B4.0BChatCodeFunctions Q4_K_M·193.7 t/s	Q4_K_M	4.2 GB9%	193.7 t/s	262K	S99, Runs great

L40 specs, power and PSU

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.

Best coding LLMs 48 GB VRAM GPUs with 48 GB or more