NVIDIA · Ada Lovelace · 8 GB VRAM tier

Best AI Models for NVIDIA GeForce RTX 4060 (8 GB)

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

8 GB GDDR6272 GB/s30 TFLOPS FP16115 WAda Lovelace 2023

What LLMs can the RTX 4060 run?

#	Model	Speed	Quant · VRAM
1	Qwen3.5 9BAlibabaHow to run → Q4_K_M · 6.6 GB · 27.8 t/s	27.8 tok/s	Q4_K_M · 6.6 GB
2	Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB · 54.2 t/s	54.2 tok/s	Q4_K_M · 3.4 GB
3	Gemma 2 9B ITGoogle Q4_K_M · 7.3 GB · 29.0 t/s	29.0 tok/s	Q4_K_M · 7.3 GB
4	Gemma 3 4B ITGoogle Q4_K_M · 5.0 GB · 62.3 t/s	62.3 tok/s	Q4_K_M · 5.0 GB
5	Ling 3.0 TinyInclusion AI Q4_K_M · 5.5 GB · 151 t/s	151 tok/s	Q4_K_M · 5.5 GB

#	Model	Speed	Reasoning Score	Quant · VRAM
1	Qwen3.5 9BAlibabaHow to run → Q4_K_M · 6.6 GB · 27.8 t/s	27.8 tok/s		Q4_K_M · 6.6 GB
2	Gemma 3 4B ITGoogle Q4_K_M · 5.0 GB · 62.3 t/s	62.3 tok/s		Q4_K_M · 5.0 GB
3	Qwen2.5 7B InstructAlibaba Q4_K_M · 5.8 GB · 35.4 t/s	35.4 tok/s		Q4_K_M · 5.8 GB
4	Gemma 2 9B ITGoogle Q4_K_M · 7.3 GB · 29.0 t/s	29.0 tok/s	overall	Q4_K_M · 7.3 GB
5	Ling 3.0 TinyInclusion AI Q4_K_M · 5.5 GB · 151 t/s	151 tok/s		Q4_K_M · 5.5 GB

#	Model	Speed	Quant · VRAM
1	Qwen3.5 4BAlibabaHow to run → Q4_K_M · 3.4 GB · 54.2 t/s	54.2 tok/s	Q4_K_M · 3.4 GB
2	Qwen3.5 9BAlibaba Q4_K_M · 6.6 GB · 27.8 t/s	27.8 tok/s	Q4_K_M · 6.6 GB
3	Ling 3.0 TinyInclusion AI Q4_K_M · 5.5 GB · 151 t/s	151 tok/s	Q4_K_M · 5.5 GB
4	Gemma 4 E4B ITGoogle Q4_K_M · 5.6 GB · 33.2 t/s	33.2 tok/s	Q4_K_M · 5.6 GB
5	MiniCPM5 2BOpenBMB Q4_K_M · 2.5 GB · 93.1 t/s	93.1 tok/s	Q4_K_M · 2.5 GB

#	Model	Speed ↓	Quant · VRAM
1	Qwen3.5 4BAlibabaHow to run → Q4_K_M · 3.4 GB · 54.2 t/s	54.2 tok/s	Q4_K_M · 3.4 GB
2	Ling 3.0 TinyInclusion AI Q4_K_M · 5.5 GB · 151 t/s	151 tok/s	Q4_K_M · 5.5 GB
3	Gemma 4 E4B ITGoogle Q4_K_M · 5.6 GB · 33.2 t/s	33.2 tok/s	Q4_K_M · 5.6 GB
4	MiMo V2.6 Distill Qwen 9BXiaomi Q4_K_M · 6.5 GB · 28.5 t/s	28.5 tok/s	Q4_K_M · 6.5 GB
5	Qwen3.5 9BAlibaba Q4_K_M · 6.6 GB · 27.8 t/s	27.8 tok/s	Q4_K_M · 6.6 GB

#	Model	Speed	Quant · VRAM
1	Qwen3.5 9BAlibabaHow to run → Q4_K_M · 6.6 GB · 27.8 t/s	27.8 tok/s	Q4_K_M · 6.6 GB
2	Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB · 54.2 t/s	54.2 tok/s	Q4_K_M · 3.4 GB
3	Gemma 3 4B ITGoogle Q4_K_M · 5.0 GB · 62.3 t/s	62.3 tok/s	Q4_K_M · 5.0 GB
4	MiMo V2.6 Distill Qwen 9BXiaomi Q4_K_M · 6.5 GB · 28.5 t/s	28.5 tok/s	Q4_K_M · 6.5 GB
5	MiniCPM V 4.7 1BOpenBMB Q4_K_M · 1.6 GB · 138 t/s	138 tok/s	Q4_K_M · 1.6 GB

See all 216 models on the RTX 4060 →Best quant that fits · speeds estimated on this card

About the RTX 4060

The RTX 4060 is an entry card in the 8 GB class: it runs 7–9B models well. It is more efficient per watt than most 8 GB cards, and pricier per token than most of the cards compared at ≈$520. Ada Lovelace generation, released 2023.

Speed in 8 GB#8272 GB/s

Per watt#40.24 tok/s per W on Qwen3.5 9B (9B params)

Per dollar#35.3 tok/s per $100 on Qwen3.5 9B (9B params)

GenerationAda Lovelacereleased 2023

RTX 4060 strengths and weaknesses

Strengths

Runs 7–9B models: Qwen3.5 9B at 27.8 tok/s in 6.6 GB
Low power draw: 115 W board power; a 250 W PSU is enough

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 5.8 s for the first token
Priced well above MSRP: ≈$520 new vs its $299 MSRP (+74%)

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 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
RTX 50608 GBBest used value	about $388	45.8	11.8	31.6
RTX 3060 12GB12 GB	about $329	36.8	11.2	21.6
RTX 507012 GB	about $736	68.7	9.3	27.5
RTX 407012 GB	about $575	51.5	9.0	25.8
RTX 40608 GB	about $335	27.8	8.3	24.2
RTX 4060 Ti 8GB8 GB	about $362	29.4	8.1	18.4
RTX 4070 SUPER12 GB	about $675	51.5	7.6	23.4
RTX 4070 Ti12 GB	about $722	51.5	7.1	18.1

Cost per token: the RTX 4060 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 card

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

$1.36

Card, new price: $1.19
Power: $0.17

3-year cost of ownership$596

Or rent in the cloud$0.09/hr

Renting costs as much as buying after ≈5,600 hours (≈3.8 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 4060, each with the one reason it is worth a look. Speeds on Qwen3.5 9B.

Faster and $60 cheaperRTX 5060NVIDIA · 8 GB · Blackwell

▲ 65% speed▼ $60 lesssame 8 GB$460

About as fast, same 8 GBRTX 4060 Ti 8GBNVIDIA · 8 GB · Ada Lovelace

▲ 6% speedsame 8 GB$399rent $0.21/hr

4 GB more and 32% fasterRTX 3060 12GBNVIDIA · 12 GB · Ampere

▲ 32% speed▲ 4 GB$329rent $0.06/hr

4 GB more and 47% fasterRX 9070 GREAMD · 12 GB · RDNA 4

▲ 47% speed▲ 4 GB$549

2 GB more and 8% fasterB570Intel · 10 GB · Xe2 (Battlemage), BMG-G21

▲ 8% speed▲ 2 GB$219

8 GB more and 2.5× the speedRTX 4070 Ti SUPERNVIDIA · 16 GB · Ada Lovelace

▲ 147% speed▲ 8 GB$799rent $0.15/hr

RTX 4060 tokens per second by model size

Output speed depends on memory bandwidth (272 GB/s). Grey rows need more than 8 GB.

9BQwen3.5 9B · Q4_K_M · 6.6 GB
27.8tok/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 822 models on the RTX 4060

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 4060 — ranked by Score, recency and Fit
Model	Quant	VRAM	Speed	Context	Fit
MN 12B Mag Mell R112.2BChatReasoning IQ2_M·36.5 t/s	IQ2_M	7.8 GB97%	36.5 t/s	1024K	B47, Decent
Codegemma 7B IT8.5BChatCode Q4_K_S·33.5 t/s	Q4_K_S	7.9 GB99%	33.5 t/s	—	C42, Usable
Qwen 7B Chat7.7BChat Q4_K_M·34.7 t/s	Q4_K_M	7.6 GB96%	34.7 t/s	33K	B48, Decent
GPT Neox 20B20.7BChat IQ2_M·23.0 t/s	IQ2_M	7.7 GB96%	23.0 t/s	2K	C38, Usable
Moonlight 16B A3B16.0BChat Q2_K·107.8 t/s	Q2_K	7.3 GB92%	107.8 t/s	8K	A75, Runs well
Baichuan2 13B Chat13BChat IQ2_M·36.6 t/s	IQ2_M	7.8 GB97%	36.6 t/s	—	B47, Decent
Granite Guardian 3.3 8B8.2BChat Q4_K_M·31.9 t/s	Q4_K_M	7.9 GB99%	31.9 t/s	131K	C42, Usable
Gemma 3 12B Pt12.2BVision IQ2_M·39.1 t/s	IQ2_M	7.4 GB93%	39.1 t/s	—	B55, Decent
Granite Guardian 3.2 8B Factuality Detection8.2BChat Q4_K_M·31.9 t/s	Q4_K_M	7.9 GB99%	31.9 t/s	131K	C42, Usable
Qwen2.5 14B Instruct14.8BChatFunctions IQ2_XS·34.5 t/s	IQ2_XS	8.0 GB99%	34.5 t/s	33K	C43, Usable
Gemma 2 9B9.2BChat Q3_K_M·35.6 t/s	Q3_K_M	7.6 GB95%	35.6 t/s	—	B51, Decent
Qwen 14B14.2BChat IQ3_S·26.7 t/s	IQ3_S	7.9 GB99%	26.7 t/s	8K	C38, Usable
Mistral Nemo Instruct 240712.2BChatFunctions IQ2_M·36.5 t/s	IQ2_M	7.8 GB97%	36.5 t/s	131K	B47, Decent
Phi 3 Medium 4k Instruct14.0BChatCode Q3_K_M·23.5 t/s	Q3_K_M	8.0 GB99%	23.5 t/s	4K	C34, Usable
Mistral Nemo Base 240712.2BChat IQ2_M·36.5 t/s	IQ2_M	7.8 GB97%	36.5 t/s	131K	B47, Decent

RTX 4060 specs, power and PSU

Specs

Architecture: Ada Lovelace
VRAM: 8 GB GDDR6
Memory bandwidth: 272.0 GB/s
FP16 (dense): 30.20 TFLOPS
CUDA cores: 3,072
Tensor cores: 96
Compute capability: 8.9
TDP: 115 W
Released: 2023-06-29
MSRP: $299

RTX 4060 FAQ

Is the RTX 4060 still worth it in 2026?

At ≈$520 you get 5.3 tok/s per $100 on Qwen3.5 9B, which ranks 3rd of the 3 cards compared here; it is also the 8th fastest out of 12 cards with 8 GB. It runs 7–9B models well; 14B doesn't fit in 8 GB.

What is the largest model the RTX 4060 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 27.8 tok/s.

Can the RTX 4060 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 4060 give?

About 27.8 tok/s on Qwen3.5 9B at Q4_K_M, with the first token after 5.8 s on a 4K-token prompt.

What power supply does the RTX 4060 need?

Plan a 250 W PSU (2× the 115 W TDP).

Is renting cheaper than buying an RTX 4060?

Rent from $0.09/hr. Renting costs as much as buying after ≈5,600 hours (≈3.8 years at 4 h a day).

Best coding LLMs 8 GB VRAM 12 GB VRAM GPUs with 8 GB or more RTX 5080 RTX 3080 Ti