llmrun

NVIDIA · Turing

Best AI Models for NVIDIA GeForce GTX 1660 SUPER (6 GB)

Runs only small models well; 7–9B only just fits.

6 GB GDDR6336 GB/s10 TFLOPS FP16125 WTuring 2019
Buyabout $229

6 GB at 336 GB/s: ~7B at Q4 is tight, but decodes quickly for its price. No Tensor Cores.

What LLMs can the GTX 1660 SUPER run?

#ModelSpeedllmrun ScoreQuant · VRAM
1
Qwen3.5 4BAlibabaHow to run →
Q4_K_M · 3.4 GB · 67.0 t/s
67.0 tok/sQ4_K_M · 3.4 GB
2
Gemma 3 4B ITGoogle
Q4_K_M · 5.0 GB · 76.9 t/s
76.9 tok/sQ4_K_M · 5.0 GB
3
Gemma 4 E2B ITGoogle
Q4_K_M · 3.5 GB · 63.7 t/s
63.7 tok/sQ4_K_M · 3.5 GB
4
Spark X2.6 4BXHToken
Q4_K_M · 4.3 GB · 73.8 t/s
73.8 tok/sQ4_K_M · 4.3 GB
5
MiniCPM5 2BOpenBMB
Q4_K_M · 2.5 GB · 115 t/s
115 tok/sQ4_K_M · 2.5 GB
See all 193 models on the GTX 1660 SUPER →Best quant that fits · speeds estimated on this card

About the GTX 1660 SUPER

The GTX 1660 SUPER is the quickest card in the 6 GB class: it runs only small models well. It is the most efficient per watt in its tier, and the best speed per dollar of the cards compared at ≈$115 used. Turing generation, released 2019.

Speed in 6 GB#1336 GB/s
Per watt#10.32 tok/s per W on Qwen3.5 9B (9B params)
Per dollar#134.4 tok/s per $100 on Qwen3.5 9B (9B params)
GenerationTuringreleased 2019

GTX 1660 SUPER strengths and weaknesses

Strengths

  • Runs 7–9B models: Qwen3.5 9B at 39.6 tok/s in 5.8 GB
  • Low power draw: 125 W board power; a 250 W PSU is enough

Weaknesses

  • 14B models don't fit: Qwen3 14B needs 11.9 GB at Q4 vs 6 GB here
  • Little room for context: Qwen3.5 9B uses 5.8 of 6 GB, 0.2 GB left
  • Slow prompt reading: A 4K-token prompt on Qwen3.5 4B waits 8.4 s for the first token
  • 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 GTX 1660 SUPER has no new price, so the New view shows it at its MSRP.

CardNew pricetok/stok/s per $100tok/s per 100 W
GTX 1660 SUPER6 GB
about $22939.6
17.3
31.7
RTX 50608 GBBest new value
about $46045.8
10.0
31.6
RTX 507012 GB
about $84068.7
8.2
27.5
RX 907016 GB
about $80060.4
7.6
27.5
RTX 40608 GB
about $52027.8
5.3
24.2
CardUsed pricetok/stok/s per $100tok/s per 100 W
GTX 1660 SUPER6 GB
about $11539.6
34.4
31.7
RTX 3060 12GB12 GB
about $32936.8
11.2
21.6
RTX 50608 GBBest used value
about $43045.8
10.7
31.6
RX 907016 GB
about $65060.4
9.3
27.5
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

Cost per token: the GTX 1660 SUPER against 6–16 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.

6 GB12 GB16 GBthis cardat MSRP
$0.00$0.50$1.00$1.50$0$1,000$ per 1M output tokens · lower is betterused price →RX 9070 · 16 GB · ≈$650 · $0.83 per 1M tokensRTX 4060 Ti 8GB · 8 GB · ≈$400 · $1.09 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 4070 · 12 GB · ≈$575 · $0.87 per 1M tokensRTX 3060 12GB · 12 GB · ≈$329 · $0.76 per 1M tokensGTX 1660 SUPER · 6 GB · ≈$115 · $0.32 per 1M tokensGTX 1660 SUPERRTX 5060RTX 5070RX 9070RTX 4070 SUPERRTX 4070 TiRTX 4070
$0.00$0.50$1.00$1.50$0$1k$ per 1M output tokens · lower is betterused price →RX 9070 · 16 GB · ≈$650 · $0.83 per 1M tokensRTX 4060 Ti 8GB · 8 GB · ≈$400 · $1.09 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 4070 · 12 GB · ≈$575 · $0.87 per 1M tokensRTX 3060 12GB · 12 GB · ≈$329 · $0.76 per 1M tokensGTX 1660 SUPER · 6 GB · ≈$115 · $0.32 per 1M tokensGTX 1660 SUPERRTX 5060RTX 5070
Cost per 1M output tokenson Qwen3.5 9B · card over 3 years + power
$0.32
Card, used price
$0.18
Power
$0.13
3-year cost of ownership$197
Or rent an RTX 3080 in the cloud$0.11/hr

Renting costs as much as buying after ≈1,100 hours (≈0.7 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 1660 SUPER, each with the one reason it is worth a look. Speeds on Qwen3.5 9B.

2 GB more and 16% fasterRTX 5060NVIDIA · 8 GB · Blackwell
▲ 16% speed▲ 2 GBabout $460
10 GB more and 53% fasterRX 9070AMD · 16 GB · RDNA 4
▲ 53% speed▲ 10 GBabout $800
2 GB more, but slowerRTX 4060 Ti 8GBNVIDIA · 8 GB · Ada Lovelace
▼ 26% speed▲ 2 GBabout $399rent $0.19/hr
2 GB more for bigger modelsA750Intel · 8 GB · Alchemist
same speed▲ 2 GBabout $289
2 GB more for bigger modelsA580Intel · 8 GB · Alchemist
same speed▲ 2 GBabout $179
2 GB more for bigger modelsRTX 4060NVIDIA · 8 GB · Ada Lovelace
▼ 30% speed▲ 2 GBabout $520rent $0.08/hr

GTX 1660 SUPER tokens per second by model size

Output speed depends on memory bandwidth (336 GB/s). Grey rows need more than 6 GB.

  1. 9BQwen3.5 9B · Q3_K_L · 5.8 GB tight · Q3_K_L
    39.6tok/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 738 models on the GTX 1660 SUPER

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 1660 SUPER — ranked by Score, recency and Fit
ModelVRAMScoreFit
Archaea 74M
Q4_K_M·624.0 t/s
0.3 GBS100, Runs great
Kimi K2.6 Eagle3
Q4_K_M·149.6 t/s
1.9 GBS97, Runs great
Tiny GptOssForCausalLM
Q4_K_M·704.5 t/s
0.3 GBS100, Runs great
SmolVLM2 256M Video Instruct
Q4_K_M·436.8 t/s
0.6 GBS100, Runs great
MobileLLM R1 360M
Q4_K_M·910.0 t/s
1.3 GBS100, Runs great
Kimi Linear Tiny Random
BF16·665.3 t/s
0.3 GBS100, Runs great
SmolLM 135M Instruct FP32
Q4_K_M·507.9 t/s
0.4 GBS100, Runs great
Functiongemma 270M IT
BF16·370.2 t/s
1.6 GBS100, Runs great
Supra Mini V5 8M
Q4_K_M·682.5 t/s
0.3 GBS100, Runs great
GPT X2 125M
BF16·341.3 t/s
0.6 GBS100, Runs great
Surya Ocr 2.5
Q4_K_M·287.4 t/s
0.8 GBS100, Runs great
LocoTrainer 4B
Q4_K_M·75.3 t/s
4.2 GBS86, Runs great
Hy MT2 1.8B
Q4_K_M·131.6 t/s
2.6 GBS95, Runs great
Quark 135M
Q4_K_M·507.9 t/s
0.4 GBS100, Runs great
Nandi Mini V1.1 600M Intermediate Checkpoint 400GT
BF16·122.7 t/s
1.8 GBS95, Runs great

GTX 1660 SUPER specs, power and PSU

Specs

Architecture
Turing
VRAM
6 GB GDDR6
Memory bandwidth
336.0 GB/s
FP16 (dense)
10.05 TFLOPS
CUDA cores
1,408
Tensor cores
0
Compute capability
7.5
TDP
125 W
Released
2019-10-29
MSRP
$229

GTX 1660 SUPER FAQ

Is the GTX 1660 SUPER still worth it in 2026?

At ≈$115 used you get 34.4 tok/s per $100 on Qwen3.5 9B, which ranks 1st of the 8 cards compared here; it is also the fastest out of 6 cards with 6 GB. It runs only small models well; 7–9B only just fits.

What is the largest model the GTX 1660 SUPER can run?

Qwen2.5 7B Instruct (7.6B) is the largest at 4-bit or better: at Q4_K_M it uses 5.8 GB of 6 GB, and runs at about 43.8 tok/s. At 3-bit, a bigger model fits too: Gemma 2 9B IT (9.2B) at IQ3_M, 5.7 GB.

Can the GTX 1660 SUPER run Qwen3.5 4B?

Yes. Qwen3.5 4B fits at Q4_K_M, using 3.4 GB of 6 GB, and it is the best model that runs well on this card.

Can the GTX 1660 SUPER run 14B models?

No. Qwen3 14B needs 11.9 GB at Q4, more than the 6 GB on this card.

How many tokens per second does the GTX 1660 SUPER give?

About 67.0 tok/s on Qwen3.5 4B at Q4_K_M, with the first token after 8.4 s on a 4K-token prompt.

What power supply does the GTX 1660 SUPER need?

Plan a 250 W PSU (2× the 125 W TDP).

Is renting cheaper than buying a GTX 1660 SUPER?

An RTX 3080 (10 GB) rents from $0.11/hr. Renting costs as much as buying after ≈1,100 hours (≈0.7 years at 4 h a day).

Related

Best coding LLMs8 GB VRAMGPUs with 6 GB or moreRTX 3080 TiRTX 3080 12GBRTX 3080