NVIDIA · Turing

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

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

6 GB GDDR6288 GB/s11 TFLOPS FP16120 WTuring 2019

6 GB at 288 GB/s: ~7B at Q4 is tight. No Tensor Cores.

What LLMs can the GTX 1660 Ti run?

#	Model	Speed	Quant · VRAM
1	Qwen3.5 4BAlibabaHow to run → Q4_K_M · 3.4 GB · 57.4 t/s	57.4 tok/s	Q4_K_M · 3.4 GB
2	Gemma 3 4B ITGoogle Q4_K_M · 5.0 GB · 65.9 t/s	65.9 tok/s	Q4_K_M · 5.0 GB
3	Gemma 4 E2B ITGoogle Q4_K_M · 3.5 GB · 54.6 t/s	54.6 tok/s	Q4_K_M · 3.5 GB
4	Spark X2.6 4BXHToken Q4_K_M · 4.3 GB · 63.2 t/s	63.2 tok/s	Q4_K_M · 4.3 GB
5	MiniCPM5 2BOpenBMB Q4_K_M · 2.5 GB · 98.5 t/s	98.5 tok/s	Q4_K_M · 2.5 GB

#	Model	Speed	Reasoning Score	Quant · VRAM
1	Gemma 3 4B ITGoogleHow to run → Q4_K_M · 5.0 GB · 65.9 t/s	65.9 tok/s		Q4_K_M · 5.0 GB
2	Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB · 57.4 t/s	57.4 tok/s	overall	Q4_K_M · 3.4 GB
3	Gemma 4 E2B ITGoogle Q4_K_M · 3.5 GB · 54.6 t/s	54.6 tok/s		Q4_K_M · 3.5 GB
4	Spark X2.6 4BXHToken Q4_K_M · 4.3 GB · 63.2 t/s	63.2 tok/s		Q4_K_M · 4.3 GB
5	MiniCPM5 2BOpenBMB Q4_K_M · 2.5 GB · 98.5 t/s	98.5 tok/s		Q4_K_M · 2.5 GB

#	Model	Speed	Quant · VRAM
1	Qwen3.5 4BAlibabaHow to run → Q4_K_M · 3.4 GB · 57.4 t/s	57.4 tok/s	Q4_K_M · 3.4 GB
2	Gemma 4 E2B ITGoogle Q4_K_M · 3.5 GB · 54.6 t/s	54.6 tok/s	Q4_K_M · 3.5 GB
3	Spark X2.6 4BXHToken Q4_K_M · 4.3 GB · 63.2 t/s	63.2 tok/s	Q4_K_M · 4.3 GB
4	MiniCPM5 2BOpenBMB Q4_K_M · 2.5 GB · 98.5 t/s	98.5 tok/s	Q4_K_M · 2.5 GB
5	MiniCPM V 4.7 1BOpenBMB Q4_K_M · 1.6 GB · 146 t/s	146 tok/s	Q4_K_M · 1.6 GB

#	Model	Speed ↓	Quant · VRAM
1	Qwen3.5 4BAlibabaHow to run → Q4_K_M · 3.4 GB · 57.4 t/s	57.4 tok/s	Q4_K_M · 3.4 GB
2	Ling 3.0 TinyInclusion AI Q4_K_M · 5.5 GB · 158 t/s	158 tok/s	Q4_K_M · 5.5 GB
3	MiniCPM5 2BOpenBMB Q4_K_M · 2.5 GB · 98.5 t/s	98.5 tok/s	Q4_K_M · 2.5 GB
4	Spark X2.6 4BXHToken Q4_K_M · 4.3 GB · 63.2 t/s	63.2 tok/s	Q4_K_M · 4.3 GB
5	Gemma 4 E2B ITGoogle Q4_K_M · 3.5 GB · 54.6 t/s	54.6 tok/s	Q4_K_M · 3.5 GB

#	Model	Speed	Quant · VRAM
1	Qwen3.5 4BAlibabaHow to run → Q4_K_M · 3.4 GB · 57.4 t/s	57.4 tok/s	Q4_K_M · 3.4 GB
2	Gemma 3 4B ITGoogle Q4_K_M · 5.0 GB · 65.9 t/s	65.9 tok/s	Q4_K_M · 5.0 GB
3	MiniCPM V 4.7 1BOpenBMB Q4_K_M · 1.6 GB · 146 t/s	146 tok/s	Q4_K_M · 1.6 GB
4	LFM3 Omni 2BLiquid AI Q4_K_M · 2.4 GB · 110 t/s	110 tok/s	Q4_K_M · 2.4 GB
5	Cosmos Reason2 2BNVIDIA Q4_K_M · 3.5 GB · 116 t/s	116 tok/s	Q4_K_M · 3.5 GB

See all 193 models on the GTX 1660 Ti →Best quant that fits · speeds estimated on this card

About the GTX 1660 Ti

The GTX 1660 Ti is a solid mid-range card in the 6 GB class: it runs only small models well. It is more efficient per watt than most 6 GB cards, and the best speed per dollar of the cards compared at ≈$120 used. Turing generation, released 2019.

Speed in 6 GB#3288 GB/s

Per watt#30.28 tok/s per W on Qwen3.5 9B (9B params)

Per dollar#128.3 tok/s per $100 on Qwen3.5 9B (9B params)

GenerationTuringreleased 2019

GTX 1660 Ti strengths and weaknesses

Strengths

Runs 7–9B models: Qwen3.5 9B at 33.9 tok/s in 5.8 GB
Low power draw: 120 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 7.8 s for the first token
No FP8 or NVFP4: Turing 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 GTX 1660 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
GTX 1660 Ti6 GB	about $279	33.9	12.2	28.3
RTX 50608 GBBest new value	about $460	45.8	10.0	31.6
RTX 507012 GB	about $840	68.7	8.2	27.5
RTX 40608 GB	about $520	27.8	5.3	24.2

Card	Used price	tok/s	tok/s per $100	tok/s per 100 W
GTX 1660 Ti6 GB	about $120	33.9	28.3	28.3
RTX 3060 12GB12 GB	about $329	36.8	11.2	21.6
RTX 50608 GBBest used value	about $430	45.8	10.7	31.6
RTX 407012 GB	about $575	51.5	9.0	25.8
RTX 40608 GB	about $335	27.8	8.3	24.2
RTX 4070 SUPER12 GB	about $675	51.5	7.6	23.4
RTX 4060 Ti 8GB8 GB	about $400	29.4	7.4	18.4
RTX 4070 Ti12 GB	about $722	51.5	7.1	18.1

Similar GPUs

Cards people weigh against the GTX 1660 Ti, each with the one reason it is worth a look. Speeds on Qwen3.5 9B.

6 GB more and 9% fasterRTX 3060 12GBNVIDIA · 12 GB · Ampere

▲ 9% speed▲ 6 GB$329rent $0.06/hr

6 GB more and 52% fasterRTX 4070NVIDIA · 12 GB · Ada Lovelace

▲ 52% speed▲ 6 GB$599rent $0.12/hr

2 GB more, but slowerRTX 4060 Ti 8GBNVIDIA · 8 GB · Ada Lovelace

▼ 13% speed▲ 2 GB$399rent $0.15/hr

2 GB more for bigger modelsRTX 4060NVIDIA · 8 GB · Ada Lovelace

▼ 18% speed▲ 2 GB$520rent $0.08/hr

2 GB more and 19% fasterA750Intel · 8 GB · Alchemist

▲ 19% speed▲ 2 GB$289

2 GB more and 19% fasterA580Intel · 8 GB · Alchemist

▲ 19% speed▲ 2 GB$179

GTX 1660 Ti tokens per second by model size

Output speed depends on memory bandwidth (288 GB/s). Grey rows need more than 6 GB.

9BQwen3.5 9B · Q3_K_L · 5.8 GB tight · Q3_K_L
33.9tok/s
14BQwen3 14B · not at 4-bit
needs 11.9 GB
27–31BQwen3.8 27B · not at 4-bit
needs 17.9 GB
35B MoEQwen3.6 35B A3B · not at 4-bit
needs 22.0 GB
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 738 models on the GTX 1660 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 GTX 1660 Ti — ranked by Score, recency and Fit
Model	Quant	VRAM	Speed	Context	Fit
TwIL 8B8.8BChatReasoningMathCodeFunctions IQ2_M·52.0 t/s	IQ2_M	6.0 GB99%	52.0 t/s	131K	C44, Usable
SmolLM 360M362MChat Q4_K_M·312.0 t/s	Q4_K_M	0.6 GB10%	312.0 t/s	2K	S100, Runs great
Yi 6B Chat6.1BChat Q4_K_M·46.0 t/s	Q4_K_M	4.2 GB70%	46.0 t/s	4K	A78, Runs well
Yi Coder 9B Chat8.8BChatCode IQ3_M·41.9 t/s	IQ3_M	5.9 GB98%	41.9 t/s	131K	C44, Usable
Internlm2 5 7B Chat7BChat Q3_K_M·47.0 t/s	Q3_K_M	5.9 GB98%	47.0 t/s	33K	C44, Usable
Qwen 1 8B1.8BChat Q4_K_M·154.7 t/s	Q4_K_M	1.9 GB32%	154.7 t/s	8K	S97, Runs great
Mistral 7B Instruct v0.37.2BChatFunctions Q3_K_M·45.7 t/s	Q3_K_M	6.0 GB100%	45.7 t/s	33K	C44, Usable
RedPajama INCITE 7B Base7BChat Q4_K_M·40.5 t/s	Q4_K_M	4.6 GB77%	40.5 t/s	2K	A75, Runs well
GPT Neox Japanese 2.7B2.7BChat BF16·31.5 t/s	BF16	5.9 GB99%	31.5 t/s	2K	C42, Usable
SmolLM2 1.7B1.7BChat Q4_K_M·108.2 t/s	Q4_K_M	2.9 GB49%	108.2 t/s	8K	S93, Runs great
Gemma 3n E4B IT7.8BVision IQ3_XXS·55.9 t/s	IQ3_XXS	5.9 GB98%	55.9 t/s	—	C44, Usable
Gemma 2B IT2.5BChat Q4_K_M·113.5 t/s	Q4_K_M	3.5 GB58%	113.5 t/s	—	S94, Runs great
CPH Community 7B7BChat Q2_K·57.2 t/s	Q2_K	5.7 GB96%	57.2 t/s	—	B58, Decent
MagicPrompt Stable Diffusion137MChat Q4_K_M·2080.0 t/s	Q4_K_M	0.1 GB2%	2080.0 t/s	1K	S100, Runs great
Mellum2 12B A2.5B Instruct12.1BChatFunctions IQ3_M·128.3 t/s	IQ3_M	5.9 GB99%	128.3 t/s	131K	C44, Usable

GTX 1660 Ti specs, power and PSU

Specs

Architecture: Turing
VRAM: 6 GB GDDR6
Memory bandwidth: 288.0 GB/s
FP16 (dense): 10.87 TFLOPS
CUDA cores: 1,536
Tensor cores: 0
Compute capability: 7.5
TDP: 120 W
Released: 2019-02-22
MSRP: $279

GTX 1660 Ti FAQ

Is the GTX 1660 Ti still worth it in 2026?

At ≈$120 used you get 28.3 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 6 cards with 6 GB. It runs only small models well; 7–9B only just fits.

What is the largest model the GTX 1660 Ti 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 37.5 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 Ti 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 Ti 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 Ti give?

About 57.4 tok/s on Qwen3.5 4B at Q4_K_M, with the first token after 7.8 s on a 4K-token prompt.

What power supply does the GTX 1660 Ti need?

Plan a 250 W PSU (2× the 120 W TDP).

Is renting cheaper than buying a GTX 1660 Ti?

An RTX 3080 Ti (12 GB) rents from $0.13/hr. Renting costs as much as buying after ≈900 hours (≈0.6 years at 4 h a day).

Best coding LLMs 8 GB VRAM GPUs with 6 GB or more RTX 3080 Ti RTX 3080 12GB RTX 3080