NVIDIA · Blackwell · 16 GB VRAM tier

Best AI Models for NVIDIA GeForce RTX 5080 (16 GB)

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

16 GB GDDR7960 GB/s113 TFLOPS FP16360 WBlackwell 2025

What LLMs can the RTX 5080 run?

#	Model	Speed	Quant · VRAM
1	Qwen3.5 9BAlibabaHow to run → Q4_K_M · 6.6 GB · 98.1 t/s	98.1 tok/s	Q4_K_M · 6.6 GB
2	Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB · 191 t/s	191 tok/s	Q4_K_M · 3.4 GB
3	GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 183 t/s	183 tok/s	Q4_K_M · 13.1 GB
4	Phi 4Microsoft Q4_K_M · 12.5 GB · 65.5 t/s	65.5 tok/s	Q4_K_M · 12.5 GB
5	Gemma 4 12B ITGoogle Q4_K_M · 9.0 GB · 75.8 t/s	75.8 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 · 183 t/s	183 tok/s		Q4_K_M · 13.1 GB
2	Llama 3.1 8B InstructMeta Q4_K_M · 7.9 GB · 118 t/s	118 tok/s		Q4_K_M · 7.9 GB
3	Qwen3.5 9BAlibaba Q4_K_M · 6.6 GB · 98.1 t/s	98.1 tok/s	overall	Q4_K_M · 6.6 GB
4	Gemma 4 12B ITGoogle Q4_K_M · 9.0 GB · 75.8 t/s	75.8 tok/s		Q4_K_M · 9.0 GB
5	MiMo V2.6 Distill Qwen 9BXiaomi Q4_K_M · 6.5 GB · 101 t/s	101 tok/s		Q4_K_M · 6.5 GB

#	Model	Speed	Quant · VRAM
1	Qwen3.5 9BAlibabaHow to run → Q4_K_M · 6.6 GB · 98.1 t/s	98.1 tok/s	Q4_K_M · 6.6 GB
2	GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 183 t/s	183 tok/s	Q4_K_M · 13.1 GB
3	Qwen3 8BAlibaba Q4_K_M · 7.6 GB · 113 t/s	113 tok/s	Q4_K_M · 7.6 GB
4	Llama 3.1 8B InstructMeta Q4_K_M · 7.9 GB · 118 t/s	118 tok/s	Q4_K_M · 7.9 GB
5	Gemma 4 12B ITGoogle Q4_K_M · 9.0 GB · 75.8 t/s	75.8 tok/s	Q4_K_M · 9.0 GB

#	Model	Speed	Quant · VRAM
1	Qwen3.5 9BAlibabaHow to run → Q4_K_M · 6.6 GB · 98.1 t/s	98.1 tok/s	Q4_K_M · 6.6 GB
2	Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB · 191 t/s	191 tok/s	Q4_K_M · 3.4 GB
3	Mistral Nemo Instruct 2407Mistral AI Q4_K_M · 11.0 GB · 77.3 t/s	77.3 tok/s	Q4_K_M · 11.0 GB
4	Llama 3.1 8B InstructMeta Q4_K_M · 7.9 GB · 118 t/s	118 tok/s	Q4_K_M · 7.9 GB
5	Gemma 4 12B ITGoogle Q4_K_M · 9.0 GB · 75.8 t/s	75.8 tok/s	Q4_K_M · 9.0 GB

#	Model	Speed ↓	Quant · VRAM
1	Qwen3.5 4BAlibabaHow to run → Q4_K_M · 3.4 GB · 191 t/s	191 tok/s	Q4_K_M · 3.4 GB
2	GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 183 t/s	183 tok/s	Q4_K_M · 13.1 GB
3	Qwen3.5 9BAlibaba Q4_K_M · 6.6 GB · 98.1 t/s	98.1 tok/s	Q4_K_M · 6.6 GB
4	Gemma 4 12B ITGoogle Q4_K_M · 9.0 GB · 75.8 t/s	75.8 tok/s	Q4_K_M · 9.0 GB
5	Phi 4Microsoft Q4_K_M · 12.5 GB · 65.5 t/s	65.5 tok/s	Q4_K_M · 12.5 GB

#	Model	Speed	Quant · VRAM
1	Qwen3.5 9BAlibabaHow to run → Q4_K_M · 6.6 GB · 98.1 t/s	98.1 tok/s	Q4_K_M · 6.6 GB
2	Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB · 191 t/s	191 tok/s	Q4_K_M · 3.4 GB
3	Gemma 3 12B ITGoogle Q4_K_M · 10.9 GB · 77.6 t/s	77.6 tok/s	Q4_K_M · 10.9 GB
4	Gemma 3 4B ITGoogle Q4_K_M · 5.0 GB · 220 t/s	220 tok/s	Q4_K_M · 5.0 GB
5	MiMo V2.6 Distill Qwen 9BXiaomi Q4_K_M · 6.5 GB · 101 t/s	101 tok/s	Q4_K_M · 6.5 GB

See all 307 models on the RTX 5080 →Best quant that fits · speeds estimated on this card

About the RTX 5080

The RTX 5080 is the quickest card in the 16 GB class: it runs 14B models well. It is more efficient per watt than most 16 GB cards, and pricier per token than most of the cards compared at ≈$1,690. Blackwell generation, released 2025.

Speed in 16 GB#1960 GB/s

Per watt#30.27 tok/s per W on Qwen3.5 9B (9B params)

Per dollar#65.8 tok/s per $100 on Qwen3.5 9B (9B params)

GenerationBlackwellreleased 2025

RTX 5080 strengths and weaknesses

Strengths

Runs 35B MoE models: Qwen3.6 35B A3B at 181 tok/s in 15.7 GB
Reads long prompts fast: A 4K-token prompt on Qwen3.5 9B starts answering in 1.6 s

Weaknesses

70B models don't fit: Llama 3.3 70B Instruct needs 51.3 GB at Q4 vs 16 GB here
Priced well above MSRP: ≈$1,690 new vs its $999 MSRP (+69%)

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.

Card	New price	tok/s	tok/s per $100	tok/s per 100 W
RTX 507012 GB	about $840	68.7	8.2	27.5
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
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
RTX 3060 12GB12 GBBest used value	about $329	36.8	11.2	21.6
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
RTX 309024 GB	about $1,500	95.7	6.4	27.3
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 509032 GB	about $6,400	183	2.9	31.8

Cost per token: the RTX 5080 against 12–32 GB cards

On Qwen3.5 9B (9B params, Q4_K_M, 4K context). Speed, cost per token and power per token depend on the model.

12 GB16 GB24 GB32 GBthis card

Cost per 1M output tokenson Qwen3.5 9B · card over 3 years + power

$1.25

Card, new price: $1.09
Power: $0.15

3-year cost of ownership$1,927

Or rent in the cloud$0.25/hr

Renting costs as much as buying after ≈6,700 hours (≈4.6 years at 4 h a day).

Include card price

Power$/kWhUseh/dayKeepyears

Each dot is a card; hover or tap it for its numbers, click to open it. Cards without a price for the chosen basis are left out. How we calculate cost per token

Similar GPUs

Cards people weigh against the RTX 5080, each with the one reason it is worth a look. Speeds on Qwen3.5 9B.

Slower but $560 cheaperRX 7900 XTXAMD · 24 GB · RDNA 3

▼ 8% speed▼ $560 less▲ 8 GB$1,130

16 GB more, 87% faster for $3,686 moreRTX 5090NVIDIA · 32 GB · Blackwell

▲ 87% speed▲ $3,686 more▲ 16 GB$5,376rent $0.48/hr

Slower but $1,100 cheaperRX 9060 XT 16GBAMD · 16 GB · RDNA 4

▼ 69% speed▼ $1,100 lesssame 16 GB$590

8 GB more, about as fastRTX 3090NVIDIA · 24 GB · Ampere

same speed▲ 8 GB$1,499rent $0.19/hr

63% slower, 12 GBRTX 3060 12GBNVIDIA · 12 GB · Ampere

▼ 62% speed▼ 4 GB$329rent $0.06/hr

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

▲ 5% speed▲ 8 GB$1,999rent $0.27/hr

RTX 5080 tokens per second by model size

Output speed depends on memory bandwidth (960 GB/s). Grey rows need more than 16 GB.

9BQwen3.5 9B · Q4_K_M · 6.6 GB
98.1tok/s
14BQwen3 14B · Q4_K_M · 11.9 GB
65.7tok/s
27–31BQwen3.8 27B · Q3_K_L · 15.4 GB tight · Q3_K_L
41.6tok/s
35B MoEQwen3.6 35B A3B · IQ3_S · 15.7 GB tight · IQ3_S
181tok/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 5080

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 5080 — ranked by Score, recency and Fit
Model	Quant	VRAM	Speed	Context	Fit
Tiny NemotronHForCausalLM Super4MChatFunctions Q4_K_M·62400.0 t/s	Q4_K_M	0.3 GB2%	62400.0 t/s	262K	S100, Runs great
Tiny NemotronHForCausalLM Ultra4MChatFunctions Q4_K_M·62400.0 t/s	Q4_K_M	0.3 GB2%	62400.0 t/s	262K	S100, Runs great
Pythia 160M213MChat Q4_K_M·4457.1 t/s	Q4_K_M	0.1 GB1%	4457.1 t/s	2K	S100, Runs great
Qwen2 VL 7B Instruct8.3BVision Q4_K_M·115.8 t/s	Q4_K_M	6.2 GB39%	115.8 t/s	33K	S94, Runs great
Granite 4.0 Micro3.4BChatFunctions Q4_K_M·248.6 t/s	Q4_K_M	3.7 GB23%	248.6 t/s	131K	S100, Runs great
Baichuan2 13B Chat13BChat Q4_K_M·72.7 t/s	Q4_K_M	11.5 GB72%	72.7 t/s	—	S86, Runs great
Qwen3.5 27B Claude 4.6 Opus Reasoning Distilled27.8BChatReasoning Q3_K_L·41.6 t/s	Q3_K_L	15.4 GB97%	41.6 t/s	262K	B50, Decent
Yi 1.5 6B Chat6.1BChat Q4_K_M·153.3 t/s	Q4_K_M	4.2 GB26%	153.3 t/s	4K	S97, Runs great
Qwen3Guard Gen 0.6B752MChat Q4_K_M·717.2 t/s	Q4_K_M	1.7 GB11%	717.2 t/s	33K	S100, Runs great
Agents A135.1BChatVisionFunctions Q3_K_S·199.9 t/s	Q3_K_S	15.8 GB99%	199.9 t/s	262K	C44, Usable
Tiny Random Phi33MChat Q4_K_M·2080.0 t/s	Q4_K_M	0.3 GB2%	2080.0 t/s	4K	S100, Runs great
SILMA 9B Instruct v1.09.2BChat Q4_K_M·96.6 t/s	Q4_K_M	7.7 GB48%	96.6 t/s	8K	S90, Runs great
Fanar 2 27B Instruct27.0BChatFunctions IQ3_M·45.2 t/s	IQ3_M	15.3 GB96%	45.2 t/s	131K	B53, Decent
Tiny Mixtral247MChat Q4_K_M·2245.4 t/s	Q4_K_M	0.5 GB3%	2245.4 t/s	131K	S100, Runs great
Granite 3.3 2B Instruct2.5BChatFunctions Q4_K_M·313.6 t/s	Q4_K_M	3.2 GB20%	313.6 t/s	131K	S100, Runs great

RTX 5080 specs, power and PSU

Specs

Architecture: Blackwell
VRAM: 16 GB GDDR7
Memory bandwidth: 960.0 GB/s
FP16 (dense): 112.60 TFLOPS
CUDA cores: 10,752
Tensor cores: 336
Compute capability: 10.0
TDP: 360 W
Released: 2025-01-30
MSRP: $999

RTX 5080 FAQ

Is the RTX 5080 still worth it in 2026?

At ≈$1,690 you get 5.8 tok/s per $100 on Qwen3.5 9B, which ranks 6th of the 8 cards compared here; it is also the fastest out of 17 cards with 16 GB. It runs 14B models well; 27–31B only just fits.

What is the largest model the RTX 5080 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 173 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 5080 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 5080 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 5080 give?

About 98.1 tok/s on Qwen3.5 9B at Q4_K_M, with the first token after 1.6 s on a 4K-token prompt.

What power supply does the RTX 5080 need?

Plan a 750 W PSU (2× the 360 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 183 tok/s. For agents, not yet: no agent-scored model fits in less than 96 GB.

Is renting cheaper than buying an RTX 5080?

Rent from $0.25/hr. Renting costs as much as buying after ≈6,700 hours (≈4.6 years at 4 h a day).

Best coding LLMs 16 GB VRAM 24 GB VRAM GPUs with 16 GB or more RTX 4090 RTX 5090 Laptop GPU