llmrun

NVIDIA · Turing · 8 GB VRAM tier

Best AI Models for NVIDIA GeForce RTX 2080 (8 GB)

Runs 7–9B models well; 14B doesn't fit in 8 GB.

8 GB GDDR6448 GB/s40 TFLOPS FP16215 WTuring 2018
Buyabout $699

Turing 8 GB: Tensor Cores and flash-attention (cc 7.5), 448 GB/s; 8 GB caps you at ~7-8B models at Q4.

What LLMs can the RTX 2080 run?

#ModelSpeedllmrun ScoreQuant · VRAM
1
Qwen3.5 9BAlibabaHow to run →
Q4_K_M · 6.6 GB · 45.8 t/s
45.8 tok/sQ4_K_M · 6.6 GB
2
Qwen3.5 4BAlibaba
Q4_K_M · 3.4 GB · 89.3 t/s
89.3 tok/sQ4_K_M · 3.4 GB
3
Gemma 2 9B ITGoogle
Q4_K_M · 7.3 GB · 47.7 t/s
47.7 tok/sQ4_K_M · 7.3 GB
4
Gemma 3 4B ITGoogle
Q4_K_M · 5.0 GB · 103 t/s
103 tok/sQ4_K_M · 5.0 GB
5
Ling 3.0 TinyInclusion AI
Q4_K_M · 5.5 GB · 221 t/s
221 tok/sQ4_K_M · 5.5 GB
See all 218 models on the RTX 2080 →Best quant that fits · speeds estimated on this card

About the RTX 2080

The RTX 2080 is a solid mid-range card in the 8 GB class: it runs 7–9B models well. It is more efficient per watt than most 8 GB cards, and the best speed per dollar of the cards compared at ≈$200 used. Turing generation, released 2018.

Speed in 8 GB#3448 GB/s
Per watt#100.21 tok/s per W on Qwen3.5 9B (9B params)
Per dollar#122.9 tok/s per $100 on Qwen3.5 9B (9B params)
GenerationTuringreleased 2018

RTX 2080 strengths and weaknesses

Strengths

  • Runs 7–9B models: Qwen3.5 9B at 45.8 tok/s in 6.6 GB

Weaknesses

  • 14B models don't fit: Qwen3 14B needs 11.9 GB at Q4 vs 8 GB here
  • Little room for context: Qwen3.5 9B uses 6.6 of 8 GB, 1.4 GB left
  • No FP8 or NVFP4: Turing predates both; use GGUF, AWQ or GPTQ builds

Speed per dollar and per watt

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 2080 has no new price, so the New view shows it at its MSRP.

CardNew pricetok/stok/s per $100tok/s per 100 W
RTX 50608 GBBest new value
about $46045.8
10.0
31.6
RTX 507012 GB
about $84068.7
8.2
27.5
RTX 20808 GB
about $69945.8
6.6
21.3
RTX 40608 GB
about $52027.8
5.3
24.2
CardUsed pricetok/stok/s per $100tok/s per 100 W
RTX 20808 GB
about $20045.8
22.9
21.3
RTX 3060 12GB12 GB
about $32936.8
11.2
21.6
RTX 50608 GBBest used value
about $43045.8
10.7
31.6
RTX 507012 GB
about $73668.7
9.3
27.5
RTX 407012 GB
about $57551.5
9.0
25.8
RTX 4070 SUPER12 GB
about $67551.5
7.6
23.4
RTX 4060 Ti 8GB8 GB
about $40029.4
7.4
18.4
RTX 4070 Ti12 GB
about $72251.5
7.1
18.1

Cost per token: the RTX 2080 against 8–12 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.

8 GB12 GBthis cardat MSRP
$0.00$0.50$1.00$1.50$0$1,000$ per 1M output tokens · lower is betterused price →RTX 5070 · 12 GB · ≈$736 · $0.83 per 1M tokensRTX 4070 · 12 GB · ≈$575 · $0.87 per 1M tokensRTX 3060 12GB · 12 GB · ≈$329 · $0.76 per 1M tokensRTX 5060 · 8 GB · ≈$430 · $0.73 per 1M tokensRTX 4070 SUPER · 12 GB · ≈$675 · $1.01 per 1M tokensRTX 4070 Ti · 12 GB · ≈$722 · $1.12 per 1M tokensRTX 4060 · 8 GB · ≈$335 · $0.94 per 1M tokensRTX 4060 Ti 8GB · 8 GB · ≈$400 · $1.09 per 1M tokensRTX 2080 · 8 GB · ≈$200 · $0.47 per 1M tokensRTX 2080RTX 5060RTX 5070RTX 4070RTX 4070 SUPERRTX 4070 TiRTX 3060 12GB
$0.00$0.50$1.00$1.50$0$1k$ per 1M output tokens · lower is betterused price →RTX 5070 · 12 GB · ≈$736 · $0.83 per 1M tokensRTX 4070 · 12 GB · ≈$575 · $0.87 per 1M tokensRTX 3060 12GB · 12 GB · ≈$329 · $0.76 per 1M tokensRTX 5060 · 8 GB · ≈$430 · $0.73 per 1M tokensRTX 4070 SUPER · 12 GB · ≈$675 · $1.01 per 1M tokensRTX 4070 Ti · 12 GB · ≈$722 · $1.12 per 1M tokensRTX 4060 · 8 GB · ≈$335 · $0.94 per 1M tokensRTX 4060 Ti 8GB · 8 GB · ≈$400 · $1.09 per 1M tokensRTX 2080 · 8 GB · ≈$200 · $0.47 per 1M tokensRTX 2080RTX 5060RTX 5070
Cost per 1M output tokenson Qwen3.5 9B · card over 3 years + power
$0.47
Card, used price
$0.28
Power
$0.20
3-year cost of ownership$341
Or rent an RTX 3090 in the cloud$0.14/hr

Renting costs as much as buying after ≈1,400 hours (≈1.0 years at 4 h a day).

Include card price

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 2080, each with the one reason it is worth a look. Speeds on Qwen3.5 9B.

4 GB more and 12% fasterRTX 4070NVIDIA · 12 GB · Ada Lovelace
▲ 12% speed▲ 4 GBabout $599rent $0.13/hr
4 GB more and 50% fasterRTX 5070NVIDIA · 12 GB · Blackwell
▲ 50% speed▲ 4 GBabout $840rent $0.17/hr
Same 8 GB, new with warrantyRTX 5060NVIDIA · 8 GB · Blackwell
same speedsame 8 GBabout $460
4 GB more, but slowerRTX 3060 12GBNVIDIA · 12 GB · Ampere
▼ 20% speed▲ 4 GBabout $329rent $0.06/hr
36% faster, same 8 GBRTX 3070 TiNVIDIA · 8 GB · Ampere
▲ 36% speedsame 8 GBabout $599rent $0.18/hr
8 GB more and 60% fasterRTX 4080NVIDIA · 16 GB · Ada Lovelace
▲ 60% speed▲ 8 GBabout $1,199rent $0.26/hr

RTX 2080 tokens per second by model size

Output speed depends on memory bandwidth (448 GB/s). Grey rows need more than 8 GB.

  1. 9BQwen3.5 9B · Q4_K_M · 6.6 GB
    45.8tok/s
  2. 14BQwen3 14B · not at 4-bit
    needs 11.9 GB
  3. 27–31BQwen3.8 27B · not at 4-bit
    needs 17.9 GB
  4. 35B MoEQwen3.6 35B A3B · not at 4-bit
    needs 22.0 GB
  5. 70BLlama 3.3 70B Instruct · not at 4-bit
    needs 51.3 GB
  6. 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 218 models on the RTX 2080

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 2080 — ranked by Score, recency and Fit
ModelVRAMScoreFit
Hy MT2 1.8B
Q4_K_M·175.4 t/s
2.6 GBS99, Runs great
MiniCPM OCR 1.0
Q4_K_M·257.7 t/s
1.5 GBS100, Runs great
Gemma 4 E4B
Q4_K_M·54.7 t/s
5.6 GBA81, Runs well
SmolVLM2 256M Video Instruct
Q4_K_M·582.4 t/s
0.6 GBS100, Runs great
Surya Ocr 2.5
Q4_K_M·383.2 t/s
0.8 GBS100, Runs great
Falcon H1 7B Instruct
Q4_K_M·57.8 t/s
6.3 GBA83, Runs well
Hy MT2 7B
Q4_K_M·54.0 t/s
7.3 GBA65, Runs well
InternVL2 1B
Q4_K_M·469.7 t/s
2.0 GBS100, Runs great
SmolVLM Instruct
Q4_K_M·142.0 t/s
4.9 GBS96, Runs great
Xiaomi OCR 0
Q4_K_M·334.7 t/s
0.9 GBS100, Runs great
Qwen3 4B Instruct 2507
Q4_K_M·100.4 t/s
4.2 GBS91, Runs great
PaddleOCR VL 1.6
Q4_K_M·327.2 t/s
1.0 GBS100, Runs great
TeleOCR
Q4_K_M·229.3 t/s
2.1 GBS100, Runs great
LightOnOCR 3 0.8B
Q4_K_M·338.6 t/s
0.9 GBS100, Runs great
OvisOCR2
Q4_K_M·338.6 t/s
0.9 GBS100, Runs great

RTX 2080 specs, power and PSU

Specs

Architecture
Turing
VRAM
8 GB GDDR6
Memory bandwidth
448.0 GB/s
FP16 (dense)
40.27 TFLOPS
CUDA cores
2,944
Tensor cores
368
Compute capability
7.5
TDP
215 W
Released
2018-09-20
MSRP
$699

RTX 2080 FAQ

Is the RTX 2080 still worth it in 2026?

At ≈$200 used you get 22.9 tok/s per $100 on Qwen3.5 9B, which ranks 1st of the 8 cards compared here; it is also the 3rd fastest out of 19 cards with 8 GB. It runs 7–9B models well; 14B doesn't fit in 8 GB.

What is the largest model the RTX 2080 can run?

Qwen3.5 9B (9.7B) is the largest at 4-bit or better: at Q4_K_M it uses 6.6 GB of 8 GB, and runs at about 45.8 tok/s.

Can the RTX 2080 run 14B models?

No. Qwen3 14B needs 11.9 GB at Q4, more than the 8 GB on this card.

How many tokens per second does the RTX 2080 give?

About 45.8 tok/s on Qwen3.5 9B at Q4_K_M, with the first token after 4.4 s on a 4K-token prompt.

What power supply does the RTX 2080 need?

Plan a 450 W PSU (2× the 215 W TDP).

Is renting cheaper than buying an RTX 2080?

An RTX 3090 (24 GB) rents from $0.14/hr. Renting costs as much as buying after ≈1,400 hours (≈1.0 years at 4 h a day).

Related

Best coding LLMs8 GB VRAM12 GB VRAMGPUs with 8 GB or moreRTX 5080RTX 3080 Ti