NVIDIA · Ada Lovelace · 16 GB VRAM tier

Best AI Models for NVIDIA GeForce RTX 4090 Laptop GPU (16 GB)

Runs 14B models well; 27–31B only just fits.

16 GB GDDR6576 GB/s79 TFLOPS FP16150 WAda Lovelace 2023

Laptop GPU is AD103 with 16 GB — NOT the desktop RTX 4090's 24 GB. Performance varies with the chassis power limit.

What LLMs can the RTX 4090 Laptop GPU run?

#	Model	Speed	Quant · VRAM
1	Qwen3.5 9BAlibabaHow to run → Q4_K_M · 6.6 GB · 58.9 t/s	58.9 tok/s	Q4_K_M · 6.6 GB
2	Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB · 115 t/s	115 tok/s	Q4_K_M · 3.4 GB
3	GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 121 t/s	121 tok/s	Q4_K_M · 13.1 GB
4	Phi 4Microsoft Q4_K_M · 12.5 GB · 39.3 t/s	39.3 tok/s	Q4_K_M · 12.5 GB
5	Gemma 4 12B ITGoogle Q4_K_M · 9.0 GB · 45.5 t/s	45.5 tok/s	Q4_K_M · 9.0 GB

#	Model	Speed	Coding Score	Quant · VRAM
1	GPT OSS 20BOpenAIHow to run → Q4_K_M · 13.1 GB · 121 t/s	121 tok/s		Q4_K_M · 13.1 GB
2	Llama 3.1 8B InstructMeta Q4_K_M · 7.9 GB · 70.6 t/s	70.6 tok/s		Q4_K_M · 7.9 GB
3	Qwen3.5 9BAlibaba Q4_K_M · 6.6 GB · 58.9 t/s	58.9 tok/s	overall	Q4_K_M · 6.6 GB
4	Gemma 4 12B ITGoogle Q4_K_M · 9.0 GB · 45.5 t/s	45.5 tok/s		Q4_K_M · 9.0 GB
5	Ling 3.0 TinyInclusion AI Q4_K_M · 5.5 GB · 262 t/s	262 tok/s		Q4_K_M · 5.5 GB

#	Model	Speed	Quant · VRAM
1	Qwen3.5 9BAlibabaHow to run → Q4_K_M · 6.6 GB · 58.9 t/s	58.9 tok/s	Q4_K_M · 6.6 GB
2	GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 121 t/s	121 tok/s	Q4_K_M · 13.1 GB
3	Qwen3 8BAlibaba Q4_K_M · 7.6 GB · 67.8 t/s	67.8 tok/s	Q4_K_M · 7.6 GB
4	Llama 3.1 8B InstructMeta Q4_K_M · 7.9 GB · 70.6 t/s	70.6 tok/s	Q4_K_M · 7.9 GB
5	Gemma 4 12B ITGoogle Q4_K_M · 9.0 GB · 45.5 t/s	45.5 tok/s	Q4_K_M · 9.0 GB

#	Model	Speed	Quant · VRAM
1	Qwen3.5 9BAlibabaHow to run → Q4_K_M · 6.6 GB · 58.9 t/s	58.9 tok/s	Q4_K_M · 6.6 GB
2	Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB · 115 t/s	115 tok/s	Q4_K_M · 3.4 GB
3	Mistral Nemo Instruct 2407Mistral AI Q4_K_M · 11.0 GB · 46.4 t/s	46.4 tok/s	Q4_K_M · 11.0 GB
4	Llama 3.1 8B InstructMeta Q4_K_M · 7.9 GB · 70.6 t/s	70.6 tok/s	Q4_K_M · 7.9 GB
5	Gemma 4 12B ITGoogle Q4_K_M · 9.0 GB · 45.5 t/s	45.5 tok/s	Q4_K_M · 9.0 GB

#	Model	Speed ↓	Quant · VRAM
1	GPT OSS 20BOpenAIHow to run → Q4_K_M · 13.1 GB · 121 t/s	121 tok/s	Q4_K_M · 13.1 GB
2	Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB · 115 t/s	115 tok/s	Q4_K_M · 3.4 GB
3	Qwen3.5 9BAlibaba Q4_K_M · 6.6 GB · 58.9 t/s	58.9 tok/s	Q4_K_M · 6.6 GB
4	Gemma 4 12B ITGoogle Q4_K_M · 9.0 GB · 45.5 t/s	45.5 tok/s	Q4_K_M · 9.0 GB
5	Phi 4Microsoft Q4_K_M · 12.5 GB · 39.3 t/s	39.3 tok/s	Q4_K_M · 12.5 GB

#	Model	Speed	Quant · VRAM
1	Qwen3.5 9BAlibabaHow to run → Q4_K_M · 6.6 GB · 58.9 t/s	58.9 tok/s	Q4_K_M · 6.6 GB
2	Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB · 115 t/s	115 tok/s	Q4_K_M · 3.4 GB
3	Gemma 3 12B ITGoogle Q4_K_M · 10.9 GB · 46.6 t/s	46.6 tok/s	Q4_K_M · 10.9 GB
4	Gemma 3 4B ITGoogle Q4_K_M · 5.0 GB · 132 t/s	132 tok/s	Q4_K_M · 5.0 GB
5	MiMo V2.6 Distill Qwen 9BXiaomi Q4_K_M · 6.5 GB · 60.3 t/s	60.3 tok/s	Q4_K_M · 6.5 GB

See all 307 models on the RTX 4090 Laptop GPU →Best quant that fits · speeds estimated on this card

About the RTX 4090 Laptop GPU

The RTX 4090 Laptop GPU runs 14B models well. Ada Lovelace generation, released 2023.

GenerationAda Lovelacereleased 2023

RTX 4090 Laptop GPU strengths and weaknesses

Strengths

Runs 35B MoE models: Qwen3.6 35B A3B at 130 tok/s in 15.7 GB
Reads long prompts fast: A 4K-token prompt on Qwen3.5 9B starts answering in 2.2 s
Low power draw: 150 W board power; a 300 W PSU is enough

Weaknesses

70B models don't fit: Llama 3.3 70B Instruct needs 51.3 GB at Q4 vs 16 GB here

Similar GPUs

Cards people weigh against the RTX 4090 Laptop GPU, each with the one reason it is worth a look.

About as fast, same 16 GBRTX 4080NVIDIA · 16 GB · Ada Lovelace

same 16 GB$1,199rent $0.24/hr73.3 tok/s

4 GB more for bigger modelsRX 7900 XTAMD · 20 GB · RDNA 3

▲ 4 GB$89975.5 tok/s

8 GB more for bigger modelsRX 7900 XTXAMD · 24 GB · RDNA 3

▲ 8 GB$1,13090.6 tok/s

8 GB more for bigger modelsRTX 5090 Laptop GPUNVIDIA · 24 GB · Blackwell

▲ 8 GB91.6 tok/s

Best value near the RTX 4090 Laptop GPURTX 5070 TiNVIDIA · 16 GB · Blackwell

same 16 GB$1,170rent $0.16/hr91.6 tok/s

8 GB more for bigger modelsRTX 3090NVIDIA · 24 GB · Ampere

▲ 8 GB$1,499rent $0.19/hr95.7 tok/s

RTX 4090 Laptop GPU tokens per second by model size

Output speed depends on memory bandwidth (576 GB/s). Grey rows need more than 16 GB.

9BQwen3.5 9B · Q4_K_M · 6.6 GB
58.9tok/s
14BQwen3 14B · Q4_K_M · 11.9 GB
39.4tok/s
27–31BQwen3.8 27B · Q3_K_L · 15.4 GB tight · Q3_K_L
25.0tok/s
35B MoEQwen3.6 35B A3B · IQ3_S · 15.7 GB tight · IQ3_S
130tok/s
70BLlama 3.3 70B Instruct · not at 4-bit
needs 51.3 GB
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 1057 models on the RTX 4090 Laptop GPU

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 GeForce RTX 4090 Laptop GPU — ranked by Score, recency and Fit
Model	Quant	VRAM	Speed	Context	Fit
SmolLM2 1.7B Instruct1.7BChat Q4_K_M·216.4 t/s	Q4_K_M	2.9 GB18%	216.4 t/s	8K	S100, Runs great
Mamba 2.8B HF2.8BChat Q4_K_M·204.6 t/s	Q4_K_M	3.7 GB23%	204.6 t/s	—	S100, Runs great
Prometheus 7B V2.07.2BChat Q4_K_M·76.3 t/s	Q4_K_M	6.8 GB42%	76.3 t/s	33K	S87, Runs great
Granite 3.1 3B A800m Instruct3.3BChatFunctions Q4_K_M·287.1 t/s	Q4_K_M	3.4 GB21%	287.1 t/s	131K	S100, Runs great
Gemma 3 4B Pt4.3BVision Q4_K_M·131.8 t/s	Q4_K_M	5 GB31%	131.8 t/s	—	S95, Runs great
MiniCPM 2B Sft BF162BChat Q4_K_M·166.4 t/s	Q4_K_M	3 GB19%	166.4 t/s	4K	S98, Runs great
BharatGPT 3B Indic3.2BChat BF16·53.0 t/s	BF16	9.1 GB57%	53.0 t/s	—	A81, Runs well
Gpt2 Medium380MChat Q4_K_M·1497.6 t/s	Q4_K_M	0.3 GB2%	1497.6 t/s	1K	S100, Runs great
LFM2.5 230M Base230MChat Q4_K_M·748.8 t/s	Q4_K_M	0.6 GB4%	748.8 t/s	128K	S100, Runs great
TinyLlama 1.1B Intermediate Step 1431k 3T1.1BChat Q4_K_M·370.7 t/s	Q4_K_M	1.0 GB6%	370.7 t/s	2K	S100, Runs great
Pythia 160M Deduped213MChat Q4_K_M·2674.3 t/s	Q4_K_M	0.1 GB1%	2674.3 t/s	2K	S100, Runs great
Mamba 1.4B HF1.4BChat Q4_K_M·411.4 t/s	Q4_K_M	2.5 GB16%	411.4 t/s	—	S100, Runs great
EuroLLM 22B Instruct 251222.6BChat Q3_K_L·30.3 t/s	Q3_K_L	15.5 GB97%	30.3 t/s	33K	B45, Decent
Apertus 8B Instruct 25098.1BChatFunctions Q4_K_M·69.3 t/s	Q4_K_M	7.3 GB46%	69.3 t/s	66K	S86, Runs great
Phi 4 Mini Reasoning3.8BChatMathCodeReasoningFunctions Q4_K_M·130.5 t/s	Q4_K_M	4.8 GB30%	130.5 t/s	131K	S95, Runs great

RTX 4090 Laptop GPU specs, power and PSU

Specs

Architecture: Ada Lovelace
VRAM: 16 GB GDDR6
Memory bandwidth: 576.0 GB/s
FP16 (dense): 79.40 TFLOPS
CUDA cores: 9,728
Tensor cores: 304
Compute capability: 8.9
TDP: 150 W
Released: 2023-02-08

RTX 4090 Laptop GPU FAQ

What is the largest model the RTX 4090 Laptop GPU can run?

Gemma 4 26B A4B IT (25.8B) is the largest at 4-bit or better: at Q4_K_S it uses 15.5 GB of 16 GB, and runs at about 117 tok/s. At 3-bit, a bigger model fits too: Gemma 2 27B IT (27.2B) at IQ3_M, 15.0 GB.

Can the RTX 4090 Laptop GPU run Qwen3.5 9B?

Yes. Qwen3.5 9B fits at Q4_K_M, using 6.6 GB of 16 GB, and it is the best model that runs well on this card.

Can the RTX 4090 Laptop GPU run 70B models?

No. Llama 3.3 70B Instruct needs 51.3 GB at Q4, more than the 16 GB on this card.

How many tokens per second does the RTX 4090 Laptop GPU give?

About 58.9 tok/s on Qwen3.5 9B at Q4_K_M, with the first token after 2.2 s on a 4K-token prompt.

What power supply does the RTX 4090 Laptop GPU need?

Plan a 300 W PSU (2× the 150 W TDP).

Is 16 GB enough for coding and agents?

Yes for coding: GPT OSS 20B, the best of the 2 coding models that fit, runs at about 121 tok/s. For agents, not yet: no agent-scored model fits in less than 96 GB.

Is renting cheaper than buying an RTX 4090 Laptop GPU?

An RTX 3090 (24 GB) rents from $0.19/hr. With regular daily use, owning pays off.

Best coding LLMs 16 GB VRAM 24 GB VRAM GPUs with 16 GB or more RTX 5090 RTX 3090 Ti