NVIDIA · Blackwell · 24 GB VRAM tier

Best AI Models for NVIDIA GeForce RTX 5090 Laptop GPU (24 GB)

Runs 27–31B and 35B MoE models well; 70B doesn't fit in 24 GB.

24 GB GDDR7896 GB/s91 TFLOPS FP16150 WBlackwell 2025

Laptop GPU: 24 GB GDDR7 but far lower clocks/power than the desktop RTX 5090 — real performance depends on the chassis power limit.

What LLMs can the RTX 5090 Laptop GPU run?

#	Model	Speed	Quant · VRAM
1	Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB · 33.4 t/s	33.4 tok/s	Q4_K_M · 17.9 GB
2	Qwen3.6 27BAlibaba Q4_K_M · 17.9 GB · 33.4 t/s	33.4 tok/s	Q4_K_M · 17.9 GB
3	Gemma 4 31B ITGoogle Q4_K_M · 21.7 GB · 28.6 t/s	28.6 tok/s	Q4_K_M · 21.7 GB
4	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 157 t/s	157 tok/s	Q4_K_M · 16.5 GB
5	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 187 t/s	187 tok/s	Q4_K_M · 19.3 GB

#	Model	Speed	Quant · VRAM
1	Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB · 33.4 t/s	33.4 tok/s	Q4_K_M · 17.9 GB
2	Gemma 4 31B ITGoogle Q4_K_M · 21.7 GB · 28.6 t/s	28.6 tok/s	Q4_K_M · 21.7 GB
3	Qwen3.6 35B A3BAlibaba Q4_K_M · 22.0 GB · 139 t/s	139 tok/s	Q4_K_M · 22.0 GB
4	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 157 t/s	157 tok/s	Q4_K_M · 16.5 GB
5	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 187 t/s	187 tok/s	Q4_K_M · 19.3 GB

#	Model	Speed	Quant · VRAM
1	Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB · 33.4 t/s	33.4 tok/s	Q4_K_M · 17.9 GB
2	Gemma 4 31B ITGoogle Q4_K_M · 21.7 GB · 28.6 t/s	28.6 tok/s	Q4_K_M · 21.7 GB
3	Qwen3.5 27BAlibaba Q4_K_M · 17.9 GB · 33.4 t/s	33.4 tok/s	Q4_K_M · 17.9 GB
4	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 157 t/s	157 tok/s	Q4_K_M · 16.5 GB
5	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 187 t/s	187 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 · 33.4 t/s	33.4 tok/s		Q4_K_M · 17.9 GB
2	Qwen3.6 27BAlibaba Q4_K_M · 17.9 GB · 33.4 t/s	33.4 tok/s		Q4_K_M · 17.9 GB
3	Qwen3.6 35B A3BAlibaba Q4_K_M · 22.0 GB · 139 t/s	139 tok/s		Q4_K_M · 22.0 GB
4	Gemma 4 31B ITGoogle Q4_K_M · 21.7 GB · 28.6 t/s	28.6 tok/s	overall	Q4_K_M · 21.7 GB
5	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 187 t/s	187 tok/s		Q4_K_M · 19.3 GB

#	Model	Speed	Quant · VRAM
1	Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB · 33.4 t/s	33.4 tok/s	Q4_K_M · 17.9 GB
2	Qwen3.6 27BAlibaba Q4_K_M · 17.9 GB · 33.4 t/s	33.4 tok/s	Q4_K_M · 17.9 GB
3	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 157 t/s	157 tok/s	Q4_K_M · 16.5 GB
4	GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 173 t/s	173 tok/s	Q4_K_M · 13.1 GB
5	LFM2.5 24B A2BLiquid AI Q4_K_M · 15.0 GB · 208 t/s	208 tok/s	Q4_K_M · 15.0 GB

#	Model	Speed ↓	Quant · VRAM
1	Qwen3.5 4BAlibabaHow to run → Q4_K_M · 3.4 GB · 179 t/s	179 tok/s	Q4_K_M · 3.4 GB
2	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 187 t/s	187 tok/s	Q4_K_M · 19.3 GB
3	GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 173 t/s	173 tok/s	Q4_K_M · 13.1 GB
4	Qwen3 30B A3B Thinking 2507Alibaba Q4_K_M · 19.4 GB · 162 t/s	162 tok/s	Q4_K_M · 19.4 GB
5	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 157 t/s	157 tok/s	Q4_K_M · 16.5 GB

#	Model	Speed	Quant · VRAM
1	Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB · 33.4 t/s	33.4 tok/s	Q4_K_M · 17.9 GB
2	Qwen3.6 27BAlibaba Q4_K_M · 17.9 GB · 33.4 t/s	33.4 tok/s	Q4_K_M · 17.9 GB
3	Gemma 4 31B ITGoogle Q4_K_M · 21.7 GB · 28.6 t/s	28.6 tok/s	Q4_K_M · 21.7 GB
4	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 157 t/s	157 tok/s	Q4_K_M · 16.5 GB
5	JEV 27B VLautotrust Q4_K_M · 17.9 GB · 33.4 t/s	33.4 tok/s	Q4_K_M · 17.9 GB

See all 327 models on the RTX 5090 Laptop GPU →Best quant that fits · speeds estimated on this card

About the RTX 5090 Laptop GPU

The RTX 5090 Laptop GPU runs 27–31B and 35B MoE models well. Blackwell generation, released 2025.

GenerationBlackwellreleased 2025

RTX 5090 Laptop GPU strengths and weaknesses

Strengths

Runs 35B MoE models: Qwen3.6 35B A3B at 139 tok/s in 22 GB
Room for long context: Qwen3.8 27B at Q4 uses 17.9 GB, leaving 6.1 GB free
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 24 GB here
Slow prompt reading: A 4K-token prompt on Qwen3.8 27B waits 5.6 s for the first token

Similar GPUs

Cards people weigh against the RTX 5090 Laptop GPU, each with the one reason it is worth a look.

About as fast, same 24 GBTITAN RTXNVIDIA · 24 GB · Turing

same 24 GB$2,499rent $0.21/hr68.7 tok/s

As fast, 20 GBRX 7900 XTAMD · 20 GB · RDNA 3

▼ 4 GB$89975.5 tok/s

Best value near the RTX 5090 Laptop GPURX 7900 XTXAMD · 24 GB · RDNA 3

same 24 GB$1,13090.6 tok/s

About as fast, same 24 GBRTX 3090NVIDIA · 24 GB · Ampere

same 24 GB$1,499rent $0.18/hr95.7 tok/s

As fast, 16 GBRTX 5080NVIDIA · 16 GB · Blackwell

▼ 8 GB$1,690rent $0.23/hr98.1 tok/s

About as fast, same 24 GBRTX 3090 TiNVIDIA · 24 GB · Ampere

same 24 GB$1,999rent $0.30/hr103 tok/s

RTX 5090 Laptop GPU tokens per second by model size

Output speed depends on memory bandwidth (896 GB/s). Grey rows need more than 24 GB.

9BQwen3.5 9B · Q4_K_M · 6.6 GB
91.6tok/s
14BQwen3 14B · Q4_K_M · 11.9 GB
61.3tok/s
27–31BQwen3.8 27B · Q4_K_M · 17.9 GB
33.4tok/s
35B MoEQwen3.6 35B A3B · Q4_K_M · 22.0 GB
139tok/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 1141 models on the RTX 5090 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 5090 Laptop GPU — ranked by Score, recency and Fit
Model	Quant	VRAM	Speed	Context	Fit
Ethereal Stardust 12B12.2BChatRoleplay Q4_K_M·72.2 t/s	Q4_K_M	11.0 GB46%	72.2 t/s	131K	S86, Runs great
Qwen3 0.6B Heretic Abliterated Uncensored596MChat Q4_K_M·746.7 t/s	Q4_K_M	1.6 GB7%	746.7 t/s	41K	S100, Runs great
Browsesafe30.5BChat Q4_K_M·162.1 t/s	Q4_K_M	19.4 GB81%	162.1 t/s	262K	S96, Runs great
LightOnOCR 2 1B1.0BVision Q4_K_M·571.0 t/s	Q4_K_M	1.8 GB8%	571.0 t/s	16K	S100, Runs great
Styx 12B12.2BChat Q4_K_M·72.2 t/s	Q4_K_M	11.0 GB46%	72.2 t/s	131K	S86, Runs great
SmolLM2 70M69MChatCode Q4_K_M·1532.6 t/s	Q4_K_M	0.5 GB2%	1532.6 t/s	8K	S100, Runs great
Tiny Random Gemma2ForCausalLM8MChat Q4_K_M·1878.7 t/s	Q4_K_M	0.3 GB1%	1878.7 t/s	8K	S100, Runs great
NVIDIA Nemotron 3.5 Lightning 30B A3B Base BF1631.6BChat Q4_K_M·187.2 t/s	Q4_K_M	19.3 GB81%	187.2 t/s	262K	S98, Runs great
Phi Tiny MoE Instruct3.8BChat Q4_K_M·292.2 t/s	Q4_K_M	3.1 GB13%	292.2 t/s	4K	S100, Runs great
Rnj 1.5 Instruct8.3BChat BF16·33.9 t/s	BF16	19.1 GB79%	33.9 t/s	164K	A73, Runs well
Dots.mocr3.0BVision Q4_K_M·267.2 t/s	Q4_K_M	2.6 GB11%	267.2 t/s	131K	S100, Runs great
Qwen3.5 9B Gemini 3.1 Pro Reasoning Distill9.7BChatReasoning Q4_K_M·91.6 t/s	Q4_K_M	6.6 GB28%	91.6 t/s	262K	S90, Runs great
Steelman 14B Ada14BChatCode Q4_K_M·63.0 t/s	Q4_K_M	12.2 GB51%	63.0 t/s	—	A84, Runs well
NVIDIA Nemotron Parse 2.0903MVision BF16·292.7 t/s	BF16	3.4 GB14%	292.7 t/s	—	S100, Runs great
SmolVLM Instruct2.2BVision Q4_K_M·284.1 t/s	Q4_K_M	4.9 GB20%	284.1 t/s	16K	S100, Runs great

RTX 5090 Laptop GPU specs, power and PSU

Specs

Architecture: Blackwell
VRAM: 24 GB GDDR7
Memory bandwidth: 896.0 GB/s
FP16 (dense): 90.70 TFLOPS
CUDA cores: 10,496
Tensor cores: 328
Compute capability: 12.0
TDP: 150 W
Released: 2025-03-01

RTX 5090 Laptop GPU FAQ

What is the largest model the RTX 5090 Laptop GPU can run?

Qwen3.6 35B A3B (36.0B) is the largest at 4-bit or better: at Q4_K_M it uses 22.0 GB of 24 GB, and runs at about 139 tok/s.

Can the RTX 5090 Laptop GPU run Qwen3.8 27B?

Yes. Qwen3.8 27B fits at Q4_K_M, using 17.9 GB of 24 GB, and it is the best model that runs well on this card.

Can the RTX 5090 Laptop GPU run 70B models?

No. Llama 3.3 70B Instruct needs 51.3 GB at Q4, more than the 24 GB on this card.

How many tokens per second does the RTX 5090 Laptop GPU give?

About 33.4 tok/s on Qwen3.8 27B at Q4_K_M, with the first token after 5.6 s on a 4K-token prompt.

What power supply does the RTX 5090 Laptop GPU need?

Plan a 300 W PSU (2× the 150 W TDP).

Is 24 GB enough for coding and agents?

Yes for coding: Qwen3.8 27B, the best of the 9 coding models that fit, runs at about 33 tok/s. For agents, not yet: no agent-scored model fits in less than 96 GB.

Is renting cheaper than buying an RTX 5090 Laptop GPU?

An A100 (80 GB) rents from $1.19/hr. With regular daily use, owning pays off.

Best coding LLMs 24 GB VRAM 48 GB VRAM GPUs with 24 GB or more RTX 5090 RTX 4090