llmrun

NVIDIA · Pascal · 8 GB VRAM tier

Best AI Models for NVIDIA GeForce GTX 1080 (8 GB)

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

8 GB GDDR5X320 GB/s9 TFLOPS FP16180 WPascal 2016
Buyabout $599

8 GB at 320 GB/s: fits ~7-8B at Q4. Pascal: no Tensor Cores and very slow FP16, so it runs GGUF (llama.cpp, Ollama) fine but not FP16 runtimes like vLLM; current CUDA 13 builds dropped Pascal — use CUDA 12 or Vulkan builds.

What LLMs can the GTX 1080 run?

#ModelSpeedllmrun ScoreQuant · VRAM
1
Qwen3.5 9BAlibabaHow to run →
Q4_K_M · 6.6 GB · 32.7 t/s
32.7 tok/sQ4_K_M · 6.6 GB
2
Qwen3.5 4BAlibaba
Q4_K_M · 3.4 GB · 63.8 t/s
63.8 tok/sQ4_K_M · 3.4 GB
3
Gemma 2 9B ITGoogle
Q4_K_M · 7.3 GB · 34.1 t/s
34.1 tok/sQ4_K_M · 7.3 GB
4
Gemma 3 4B ITGoogle
Q4_K_M · 5.0 GB · 73.2 t/s
73.2 tok/sQ4_K_M · 5.0 GB
5
Ling 3.0 TinyInclusion AI
Q4_K_M · 5.5 GB · 172 t/s
172 tok/sQ4_K_M · 5.5 GB
See all 218 models on the GTX 1080 →Best quant that fits · speeds estimated on this card

About the GTX 1080

The GTX 1080 is an entry card in the 8 GB class: it runs 7–9B models well. It is power-hungry for its speed, and the best speed per dollar of the cards compared at ≈$115 used. Pascal generation, released 2016.

Speed in 8 GB#11320 GB/s
Per watt#150.18 tok/s per W on Qwen3.5 9B (9B params)
Per dollar#128.4 tok/s per $100 on Qwen3.5 9B (9B params)
GenerationPascalreleased 2016

GTX 1080 strengths and weaknesses

Strengths

  • Runs 7–9B models: Qwen3.5 9B at 32.7 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
  • Slow prompt reading: A 4K-token prompt on Qwen3.5 9B waits 19.8 s for the first token
  • No FP8 or NVFP4: Pascal 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 GTX 1080 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
GTX 10808 GB
about $59932.7
5.5
18.2
RTX 40608 GB
about $52027.8
5.3
24.2
CardUsed pricetok/stok/s per $100tok/s per 100 W
GTX 10808 GB
about $11532.7
28.4
18.2
RTX 3060 12GB12 GB
about $32936.8
11.2
21.6
RTX 50608 GBBest used value
about $43045.8
10.7
31.6
RTX 407012 GB
about $57551.5
9.0
25.8
RTX 40608 GB
about $33527.8
8.3
24.2
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 GTX 1080 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 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 5070 · 12 GB · ≈$736 · $0.83 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 tokensGTX 1080 · 8 GB · ≈$115 · $0.45 per 1M tokensGTX 1080RTX 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 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 5070 · 12 GB · ≈$736 · $0.83 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 tokensGTX 1080 · 8 GB · ≈$115 · $0.45 per 1M tokensGTX 1080RTX 5060RTX 5070
Cost per 1M output tokenson Qwen3.5 9B · card over 3 years + power
$0.45
Card, used price
$0.22
Power
$0.23
3-year cost of ownership$233
Or rent an RTX 5080 in the cloud$0.22/hr

Renting costs as much as buying after ≈500 hours (≈0.4 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 GTX 1080, each with the one reason it is worth a look. Speeds on Qwen3.5 9B.

4 GB more and 13% fasterRTX 3060 12GBNVIDIA · 12 GB · Ampere
▲ 13% speed▲ 4 GBabout $329rent $0.06/hr
4 GB more and 58% fasterRTX 4070NVIDIA · 12 GB · Ada Lovelace
▲ 58% speed▲ 4 GBabout $599rent $0.13/hr
4 GB more and 25% fasterRX 9070 GREAMD · 12 GB · RDNA 4
▲ 25% speed▲ 4 GBabout $549
23% faster, same 8 GBA580Intel · 8 GB · Alchemist
▲ 23% speedsame 8 GBabout $179
8 GB more and 2.2× the speedRTX 4080NVIDIA · 16 GB · Ada Lovelace
▲ 124% speed▲ 8 GBabout $1,199rent $0.27/hr
8 GB more and 2.3× the speedRTX 4080 SUPERNVIDIA · 16 GB · Ada Lovelace
▲ 130% speed▲ 8 GBabout $999rent $0.22/hr

GTX 1080 tokens per second by model size

Output speed depends on memory bandwidth (320 GB/s). Grey rows need more than 8 GB.

  1. 9BQwen3.5 9B · Q4_K_M · 6.6 GB
    32.7tok/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 842 models on the GTX 1080

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 GTX 1080 — ranked by Score, recency and Fit
ModelVRAMScoreFit
Qwen 14B
IQ3_S·31.4 t/s
7.9 GBC42, Usable
Gemma 2 9B
Q3_K_M·41.9 t/s
7.6 GBB53, Decent
Mistral Nemo Instruct 2407
IQ2_M·42.9 t/s
7.8 GBB50, Decent
Phi 3 Medium 4k Instruct
Q3_K_M·27.6 t/s
8.0 GBC38, Usable
Mistral Nemo Base 2407
IQ2_M·42.9 t/s
7.8 GBB50, Decent
Qwen 14B Chat
IQ3_S·31.4 t/s
7.9 GBC42, Usable
DeepSeek v2 Lite
Q2_K·132.7 t/s
7.5 GBB62, Decent
ERNIE 4.5 21B A3B PT
IQ2_S·179.3 t/s
7.8 GBC44, Usable
Qwen2.5 14B Instruct 1M
IQ2_XS·40.5 t/s
8.0 GBC44, Usable
Phi 3.5 Mini Instruct
IQ2_S·90.4 t/s
7.9 GBC44, Usable
Phi 3 Medium 128k Instruct
IQ2_XS·42.4 t/s
7.8 GBC44, Usable
Qwen3 14B Base
IQ2_M·37.0 t/s
8.0 GBC43, Usable
Phi 3 Mini 128k Instruct
IQ2_S·90.4 t/s
7.9 GBC44, Usable
DeepSeek Coder v2 Lite Base
Q2_K·132.7 t/s
7.5 GBB62, Decent
Qwen2.5 14B
IQ2_XS·40.5 t/s
8.0 GBC44, Usable

GTX 1080 specs, power and PSU

Specs

Architecture
Pascal
VRAM
8 GB GDDR5X
Memory bandwidth
320.0 GB/s
FP16 (dense)
8.87 TFLOPS
CUDA cores
2,560
Tensor cores
0
Compute capability
6.1
TDP
180 W
Released
2016-05-27
MSRP
$599

GTX 1080 FAQ

Is the GTX 1080 still worth it in 2026?

At ≈$115 used you get 28.4 tok/s per $100 on Qwen3.5 9B, which ranks 1st of the 8 cards compared here; it is also the 11th 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 GTX 1080 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 32.7 tok/s.

Can the GTX 1080 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 GTX 1080 give?

About 32.7 tok/s on Qwen3.5 9B at Q4_K_M, with the first token after 19.8 s on a 4K-token prompt.

What power supply does the GTX 1080 need?

Plan a 400 W PSU (2× the 180 W TDP).

Is renting cheaper than buying a GTX 1080?

An RTX 5080 (16 GB) rents from $0.22/hr. Renting costs as much as buying after ≈500 hours (≈0.4 years at 4 h a day).

Related

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