Best AI Models for NVIDIA GeForce RTX 3090 Ti (24 GB)

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

24 GB GDDR6X1008 GB/s80 TFLOPS FP16450 WAmpere 2022

What LLMs can the RTX 3090 Ti run?

#	Model	Speed	Quant · VRAM
1	Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB · 37.6 t/s	37.6 tok/s	Q4_K_M · 17.9 GB
2	Qwen3.6 27BAlibaba Q4_K_M · 17.9 GB · 37.6 t/s	37.6 tok/s	Q4_K_M · 17.9 GB
3	Gemma 4 31B ITGoogle Q4_K_M · 21.7 GB · 32.1 t/s	32.1 tok/s	Q4_K_M · 21.7 GB
4	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 171 t/s	171 tok/s	Q4_K_M · 16.5 GB
5	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 197 t/s	197 tok/s	Q4_K_M · 19.3 GB

#	Model	Speed	Quant · VRAM
1	Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB · 37.6 t/s	37.6 tok/s	Q4_K_M · 17.9 GB
2	Gemma 4 31B ITGoogle Q4_K_M · 21.7 GB · 32.1 t/s	32.1 tok/s	Q4_K_M · 21.7 GB
3	Qwen3.6 35B A3BAlibaba Q4_K_M · 22.0 GB · 151 t/s	151 tok/s	Q4_K_M · 22.0 GB
4	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 171 t/s	171 tok/s	Q4_K_M · 16.5 GB
5	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 197 t/s	197 tok/s	Q4_K_M · 19.3 GB

#	Model	Speed	Quant · VRAM
1	Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB · 37.6 t/s	37.6 tok/s	Q4_K_M · 17.9 GB
2	Gemma 4 31B ITGoogle Q4_K_M · 21.7 GB · 32.1 t/s	32.1 tok/s	Q4_K_M · 21.7 GB
3	Qwen3.5 27BAlibaba Q4_K_M · 17.9 GB · 37.6 t/s	37.6 tok/s	Q4_K_M · 17.9 GB
4	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 171 t/s	171 tok/s	Q4_K_M · 16.5 GB
5	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 197 t/s	197 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 · 37.6 t/s	37.6 tok/s		Q4_K_M · 17.9 GB
2	Qwen3.6 27BAlibaba Q4_K_M · 17.9 GB · 37.6 t/s	37.6 tok/s		Q4_K_M · 17.9 GB
3	Qwen3.6 35B A3BAlibaba Q4_K_M · 22.0 GB · 151 t/s	151 tok/s		Q4_K_M · 22.0 GB
4	Gemma 4 31B ITGoogle Q4_K_M · 21.7 GB · 32.1 t/s	32.1 tok/s	overall	Q4_K_M · 21.7 GB
5	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 197 t/s	197 tok/s		Q4_K_M · 19.3 GB

#	Model	Speed	Quant · VRAM
1	Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB · 37.6 t/s	37.6 tok/s	Q4_K_M · 17.9 GB
2	Qwen3.6 27BAlibaba Q4_K_M · 17.9 GB · 37.6 t/s	37.6 tok/s	Q4_K_M · 17.9 GB
3	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 171 t/s	171 tok/s	Q4_K_M · 16.5 GB
4	GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 190 t/s	190 tok/s	Q4_K_M · 13.1 GB
5	LFM2.5 24B A2BLiquid AI Q4_K_M · 15.0 GB · 221 t/s	221 tok/s	Q4_K_M · 15.0 GB

#	Model	Speed ↓	Quant · VRAM
1	Qwen3.5 4BAlibabaHow to run → Q4_K_M · 3.4 GB · 201 t/s	201 tok/s	Q4_K_M · 3.4 GB
2	NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA Q4_K_M · 19.3 GB · 197 t/s	197 tok/s	Q4_K_M · 19.3 GB
3	GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 190 t/s	190 tok/s	Q4_K_M · 13.1 GB
4	Qwen3 30B A3B Thinking 2507Alibaba Q4_K_M · 19.4 GB · 173 t/s	173 tok/s	Q4_K_M · 19.4 GB
5	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 171 t/s	171 tok/s	Q4_K_M · 16.5 GB

#	Model	Speed	Quant · VRAM
1	Qwen3.8 27BAlibabaHow to run → Q4_K_M · 17.9 GB · 37.6 t/s	37.6 tok/s	Q4_K_M · 17.9 GB
2	Qwen3.6 27BAlibaba Q4_K_M · 17.9 GB · 37.6 t/s	37.6 tok/s	Q4_K_M · 17.9 GB
3	Gemma 4 31B ITGoogle Q4_K_M · 21.7 GB · 32.1 t/s	32.1 tok/s	Q4_K_M · 21.7 GB
4	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 171 t/s	171 tok/s	Q4_K_M · 16.5 GB
5	JEV 27B VLautotrust Q4_K_M · 17.9 GB · 37.6 t/s	37.6 tok/s	Q4_K_M · 17.9 GB

See all 327 models on the RTX 3090 Ti →Best quant that fits · speeds estimated on this card

About the RTX 3090 Ti

The RTX 3090 Ti is the quickest card in the 24 GB class: it runs 27–31B and 35B MoE models well. It is power-hungry for its speed, and fair value at ≈$1,600 used. Ampere generation, released 2022.

Speed in 24 GB#11008 GB/s

Per watt#40.23 tok/s per W on Qwen3.5 9B (9B params)

Per dollar#46.4 tok/s per $100 on Qwen3.5 9B (9B params)

GenerationAmperereleased 2022

RTX 3090 Ti strengths and weaknesses

Strengths

Runs 35B MoE models: Qwen3.6 35B A3B at 151 tok/s in 22 GB
Room for long context: Qwen3.8 27B at Q4 uses 17.9 GB, leaving 6.1 GB free

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 6.3 s for the first token
450 W under load: Plan a 900 W PSU; ≈$99 a year at 4 h a day
No FP8 or NVFP4: Ampere predates both; use GGUF, AWQ or GPTQ builds

Speed per dollar and per watt

NewUsed

On Qwen3.5 9B (9B params) at Q4_K_M. New prices are compared with new, used with used. The last two columns are the speed you get per $100 of price and per 100 W of board power; higher is better. The RTX 3090 Ti has no new price, so the New view shows it at its MSRP.

Card	New price	tok/s	tok/s per $100	tok/s per 100 W
RX 7900 XTX24 GB	about $1,130	90.6	8.0	25.5
RTX 5070 Ti16 GBBest new value	about $1,170	91.6	7.8	30.5
RX 907016 GB	about $800	60.4	7.6	27.5
RX 9070 XT16 GB	about $815	60.4	7.4	19.9
RTX 508016 GB	about $1,690	98.1	5.8	27.3
RTX 3090 Ti24 GB	about $1,999	103	5.2	22.9
RX 9060 XT 16GB16 GB	about $590	30.2	5.1	18.9
RTX 509032 GB	about $5,376	183	3.4	31.8

Card	Used price	tok/s	tok/s per $100	tok/s per 100 W
RX 907016 GBBest used value	about $650	60.4	9.3	27.5
RX 7900 XTX24 GB	about $1,000	90.6	9.1	25.5
RTX 5070 Ti16 GB	about $1,100	91.6	8.3	30.5
RTX 3090 Ti24 GB	about $1,600	103	6.4	22.9
RX 9060 XT 16GB16 GB	about $480	30.2	6.3	18.9
RTX 508016 GB	about $1,640	98.1	6.0	27.3
RTX 409024 GB	about $3,000	103	3.4	22.9
RTX 509032 GB	about $6,400	183	2.9	31.8

Similar GPUs

Cards people weigh against the RTX 3090 Ti, each with the one reason it is worth a look. Speeds on Qwen3.5 9B.

8 GB more and 78% fasterRTX 5090NVIDIA · 32 GB · Blackwell

▲ 78% speed▲ 8 GB$5,376rent $0.50/hr

12% slower, same 24 GBRX 7900 XTXAMD · 24 GB · RDNA 3

▼ 12% speedsame 24 GB$1,130

71% slower, 16 GBRX 9060 XT 16GBAMD · 16 GB · RDNA 4

▼ 71% speed▼ 8 GB$590

About as fast, same 24 GBRTX 4090NVIDIA · 24 GB · Ada Lovelace

same speedsame 24 GB$1,599rent $0.37/hr

RTX 3090 Ti tokens per second by model size

Output speed depends on memory bandwidth (1008 GB/s). Grey rows need more than 24 GB.

9BQwen3.5 9B · Q4_K_M · 6.6 GB
103tok/s
14BQwen3 14B · Q4_K_M · 11.9 GB
69.0tok/s
27–31BQwen3.8 27B · Q4_K_M · 17.9 GB
37.6tok/s
35B MoEQwen3.6 35B A3B · Q4_K_M · 22.0 GB
151tok/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 3090 Ti

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 3090 Ti — ranked by Score, recency and Fit
Model	Quant	VRAM	Speed	Context	Fit
Qwen1.5 14B14.2BChat Q4_K_M·62.5 t/s	Q4_K_M	22.2 GB93%	62.5 t/s	33K	B62, Decent
Hermes 2 Theta Llama 3 70B70.6BChatFunctions IQ2_XXS·32.2 t/s	IQ2_XXS	22.4 GB93%	32.2 t/s	8K	B52, Decent
Mixtral 8x7B v0.146.7BChat IQ3_M·92.2 t/s	IQ3_M	23.5 GB98%	92.2 t/s	33K	C44, Usable
Qwen1.5 32B32.5BChat Q4_K_S·34.3 t/s	Q4_K_S	22.9 GB95%	34.3 t/s	33K	B50, Decent
Qwen2.5 32B32.8BChat Q3_K_M·39.0 t/s	Q3_K_M	20.6 GB86%	39.0 t/s	131K	A67, Runs well
Deepseek Coder 6.7B Base6.7BChatCode Q4_K_M·120.9 t/s	Q4_K_M	12.9 GB54%	120.9 t/s	16K	S95, Runs great
Qwen2.5 Coder 32B32.8BChatCodeFunctions Q4_K_S·34.0 t/s	Q4_K_S	23.0 GB96%	34.0 t/s	33K	B48, Decent
Deepseek Coder 33B Base33.3BChatCode Q4_K_S·33.5 t/s	Q4_K_S	23.2 GB97%	33.5 t/s	16K	B46, Decent
CodeLlama 70B Instruct HF69.0BChatCode IQ2_S·29.1 t/s	IQ2_S	23.2 GB97%	29.1 t/s	4K	C44, Usable
Deepseek Coder 1.3B Base1.3BChatCode Q4_K_M·442.7 t/s	Q4_K_M	4.3 GB18%	442.7 t/s	16K	S100, Runs great
Falcon 40B41.8BChat IQ3_S·33.5 t/s	IQ3_S	23.6 GB99%	33.5 t/s	—	C42, Usable
Meta Llama Guard 2 8B8.0BChat BF16·37.1 t/s	BF16	20.2 GB84%	37.1 t/s	—	A69, Runs well
StableBeluga270BChat IQ2_S·28.7 t/s	IQ2_S	23.5 GB98%	28.7 t/s	4K	C41, Usable
Meta Llama 3 70B Instruct70.6BChat IQ2_XXS·32.2 t/s	IQ2_XXS	22.4 GB93%	32.2 t/s	8K	B52, Decent
Mellum2 12B A2.5B Base12.1BChat BF16·—	BF16	24.8 GB103%	—	131K	F0, Won't fit

RTX 3090 Ti specs, power and PSU

Specs

Architecture: Ampere
VRAM: 24 GB GDDR6X
Memory bandwidth: 1008.0 GB/s
FP16 (dense): 80.00 TFLOPS
CUDA cores: 10,752
Tensor cores: 336
Compute capability: 8.6
TDP: 450 W
Released: 2022-03-29
MSRP: $1,999

RTX 3090 Ti FAQ

Is the RTX 3090 Ti still worth it in 2026?

At ≈$1,600 used you get 6.4 tok/s per $100 on Qwen3.5 9B, which ranks 4th of the 8 cards compared here; it is also the fastest out of 5 cards with 24 GB. It runs 27–31B and 35B MoE models well; 70B doesn't fit in 24 GB.

What is the largest model the RTX 3090 Ti 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 151 tok/s.

Can the RTX 3090 Ti 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 3090 Ti 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 3090 Ti give?

About 37.6 tok/s on Qwen3.8 27B at Q4_K_M, with the first token after 6.3 s on a 4K-token prompt.

What power supply does the RTX 3090 Ti need?

Plan a 900 W PSU (2× the 450 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 38 tok/s. For agents, not yet: no agent-scored model fits in less than 96 GB.

Is renting cheaper than buying an RTX 3090 Ti?

Rent from $0.30/hr. Renting costs as much as buying after ≈5,300 hours (≈3.7 years at 4 h a day).

Best coding LLMs 24 GB VRAM 48 GB VRAM GPUs with 24 GB or more