NVIDIA · Ada Lovelace · 12 GB VRAM tier

Best AI Models for NVIDIA GeForce RTX 4070 Ti (12 GB)

Runs 7–9B models well; 14B only just fits.

12 GB GDDR6X504 GB/s80 TFLOPS FP16285 WAda Lovelace 2023

What LLMs can the RTX 4070 Ti run?

#	Model	Speed	Quant · VRAM
1	Qwen3.5 9BAlibabaHow to run → Q4_K_M · 6.6 GB · 51.5 t/s	51.5 tok/s	Q4_K_M · 6.6 GB
2	Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB · 101 t/s	101 tok/s	Q4_K_M · 3.4 GB
3	Gemma 3 12B ITGoogle Q4_K_M · 10.9 GB · 40.7 t/s	40.7 tok/s	Q4_K_M · 10.9 GB
4	Gemma 2 9B ITGoogle Q4_K_M · 7.3 GB · 53.7 t/s	53.7 tok/s	Q4_K_M · 7.3 GB
5	Ling 3.0 TinyInclusion AI Q4_K_M · 5.5 GB · 240 t/s	240 tok/s	Q4_K_M · 5.5 GB

#	Model	Speed	Coding Score	Quant · VRAM
1	Llama 3.1 8B InstructMetaHow to run → Q4_K_M · 7.9 GB · 61.8 t/s	61.8 tok/s		Q4_K_M · 7.9 GB
2	Qwen3.5 9BAlibaba Q4_K_M · 6.6 GB · 51.5 t/s	51.5 tok/s	overall	Q4_K_M · 6.6 GB
3	Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB · 101 t/s	101 tok/s	overall	Q4_K_M · 3.4 GB
4	Gemma 4 12B ITGoogle Q4_K_M · 9.0 GB · 39.8 t/s	39.8 tok/s		Q4_K_M · 9.0 GB
5	Ling 3.0 TinyInclusion AI Q4_K_M · 5.5 GB · 240 t/s	240 tok/s		Q4_K_M · 5.5 GB

#	Model	Speed	Quant · VRAM
1	Qwen3.5 9BAlibabaHow to run → Q4_K_M · 6.6 GB · 51.5 t/s	51.5 tok/s	Q4_K_M · 6.6 GB
2	Qwen3 8BAlibaba Q4_K_M · 7.6 GB · 59.3 t/s	59.3 tok/s	Q4_K_M · 7.6 GB
3	Llama 3.1 8B InstructMeta Q4_K_M · 7.9 GB · 61.8 t/s	61.8 tok/s	Q4_K_M · 7.9 GB
4	Gemma 3 4B ITGoogle Q4_K_M · 5.0 GB · 115 t/s	115 tok/s	Q4_K_M · 5.0 GB
5	Gemma 4 12B ITGoogle Q4_K_M · 9.0 GB · 39.8 t/s	39.8 tok/s	Q4_K_M · 9.0 GB

#	Model	Speed	Quant · VRAM
1	Qwen3.5 9BAlibabaHow to run → Q4_K_M · 6.6 GB · 51.5 t/s	51.5 tok/s	Q4_K_M · 6.6 GB
2	Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB · 101 t/s	101 tok/s	Q4_K_M · 3.4 GB
3	Llama 3.1 8B InstructMeta Q4_K_M · 7.9 GB · 61.8 t/s	61.8 tok/s	Q4_K_M · 7.9 GB
4	Mistral Nemo Instruct 2407Mistral AI Q4_K_M · 11.0 GB · 40.6 t/s	40.6 tok/s	Q4_K_M · 11.0 GB
5	Gemma 4 12B ITGoogle Q4_K_M · 9.0 GB · 39.8 t/s	39.8 tok/s	Q4_K_M · 9.0 GB

#	Model	Speed ↓	Quant · VRAM
1	Qwen3.5 4BAlibabaHow to run → Q4_K_M · 3.4 GB · 101 t/s	101 tok/s	Q4_K_M · 3.4 GB
2	Ling 3.0 TinyInclusion AI Q4_K_M · 5.5 GB · 240 t/s	240 tok/s	Q4_K_M · 5.5 GB
3	Qwen3 8BAlibaba Q4_K_M · 7.6 GB · 59.3 t/s	59.3 tok/s	Q4_K_M · 7.6 GB
4	Qwen3.5 9BAlibaba Q4_K_M · 6.6 GB · 51.5 t/s	51.5 tok/s	Q4_K_M · 6.6 GB
5	Gemma 4 12B ITGoogle Q4_K_M · 9.0 GB · 39.8 t/s	39.8 tok/s	Q4_K_M · 9.0 GB

#	Model	Speed	Quant · VRAM
1	Qwen3.5 9BAlibabaHow to run → Q4_K_M · 6.6 GB · 51.5 t/s	51.5 tok/s	Q4_K_M · 6.6 GB
2	Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB · 101 t/s	101 tok/s	Q4_K_M · 3.4 GB
3	Gemma 3 12B ITGoogle Q4_K_M · 10.9 GB · 40.7 t/s	40.7 tok/s	Q4_K_M · 10.9 GB
4	Gemma 3 4B ITGoogle Q4_K_M · 5.0 GB · 115 t/s	115 tok/s	Q4_K_M · 5.0 GB
5	MiMo V2.6 Distill Qwen 9BXiaomi Q4_K_M · 6.5 GB · 52.8 t/s	52.8 tok/s	Q4_K_M · 6.5 GB

See all 276 models on the RTX 4070 Ti →Best quant that fits · speeds estimated on this card

About the RTX 4070 Ti

The RTX 4070 Ti is a solid mid-range card in the 12 GB class: it runs 7–9B models well. It is power-hungry for its speed, and pricier per token than most of the cards compared at ≈$722 used. Ada Lovelace generation, released 2023.

Speed in 12 GB#3504 GB/s

Per watt#80.18 tok/s per W on Qwen3.5 9B (9B params)

Per dollar#77.1 tok/s per $100 on Qwen3.5 9B (9B params)

GenerationAda Lovelacereleased 2023

RTX 4070 Ti strengths and weaknesses

Strengths

Runs 14B models: Qwen3 14B at 34.5 tok/s in 11.9 GB
Reads long prompts fast: A 4K-token prompt on Qwen3.5 9B starts answering in 2.2 s

Weaknesses

27–31B models don't fit: Qwen3.8 27B needs 17.9 GB at Q4 vs 12 GB here
Little room for context: Qwen3 14B uses 11.9 of 12 GB, 0.1 GB left
Used prices still near MSRP: ≈$722 used vs its $799 MSRP

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 RTX 4070 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
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 5070 Ti16 GB	about $1,170	91.6	7.8	30.5
RX 907016 GB	about $800	60.4	7.6	27.5
RX 9070 XT16 GB	about $815	60.4	7.4	19.9
RTX 4070 Ti12 GB	about $799	51.5	6.4	18.1
RTX 40608 GB	about $520	27.8	5.3	24.2
RX 9060 XT 16GB16 GB	about $590	30.2	5.1	18.9

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
RX 907016 GB	about $650	60.4	9.3	27.5
RTX 407012 GB	about $575	51.5	9.0	25.8
RTX 4070 SUPER12 GB	about $675	51.5	7.6	23.4
RTX 4070 Ti12 GB	about $722	51.5	7.1	18.1
RX 9060 XT 16GB16 GB	about $480	30.2	6.3	18.9

Similar GPUs

Cards people weigh against the RTX 4070 Ti, each with the one reason it is worth a look. Speeds on Qwen3.5 9B.

About as fast, same 12 GBRTX 4070NVIDIA · 12 GB · Ada Lovelace

same speedsame 12 GB$599rent $0.13/hr

4 GB more and 17% fasterRX 9070AMD · 16 GB · RDNA 4

▲ 17% speed▲ 4 GB$800

29% slower, same 12 GBRTX 3060 12GBNVIDIA · 12 GB · Ampere

▼ 28% speedsame 12 GB$329rent $0.06/hr

Same 12 GB, new with warrantyRTX 5070NVIDIA · 12 GB · Blackwell

▲ 33% speedsame 12 GB$840rent $0.17/hr

4 GB more, but slowerRX 9060 XT 16GBAMD · 16 GB · RDNA 4

▼ 41% speed▲ 4 GB$590

12 GB more and 76% fasterRX 7900 XTXAMD · 24 GB · RDNA 3

▲ 76% speed▲ 12 GB$1,130

RTX 4070 Ti tokens per second by model size

Output speed depends on memory bandwidth (504 GB/s). Grey rows need more than 12 GB.

9BQwen3.5 9B · Q4_K_M · 6.6 GB
51.5tok/s
14BQwen3 14B · Q4_K_M · 11.9 GB tight · Q4_K_M
34.5tok/s
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 956 models on the RTX 4070 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 RTX 4070 Ti — ranked by Score, recency and Fit
Model	Quant	VRAM	Speed	Context	Fit
Llama Guard 3 1B1.5BChat Q4_K_M·258.0 t/s	Q4_K_M	1.7 GB14%	258.0 t/s	131K	S100, Runs great
LFM2.5 1.2B Base1.2BChat Q4_K_M·306.2 t/s	Q4_K_M	1.2 GB10%	306.2 t/s	128K	S100, Runs great
Granite 3.3 8B Instruct8.2BChatFunctions Q4_K_M·59.1 t/s	Q4_K_M	7.9 GB66%	59.1 t/s	131K	A83, Runs well
Mistral 7B v0.37.2BChat Q4_K_M·66.6 t/s	Q4_K_M	6.8 GB57%	66.6 t/s	33K	S85, Runs great
Qwen2.5 Coder 3B Instruct3.1BChatCodeFunctions Q4_K_M·146.9 t/s	Q4_K_M	2.8 GB23%	146.9 t/s	33K	S97, Runs great
Qwen3 8B Base8.2BChat Q4_K_M·59.3 t/s	Q4_K_M	7.6 GB64%	59.3 t/s	33K	A84, Runs well
Gemma 3 270M IT270MChat Q4_K_M·1820.0 t/s	Q4_K_M	1.2 GB10%	1820.0 t/s	—	S100, Runs great
Hy MT2 30B A3B30.1BTranslationFunctions IQ2_M·157.8 t/s	IQ2_M	11.3 GB94%	157.8 t/s	262K	B62, Decent
LFM2 350M Extract354MChat Q4_K_M·564.8 t/s	Q4_K_M	0.8 GB6%	564.8 t/s	128K	S100, Runs great
Mellum2 12B A2.5B Instruct SFT12.1BChat Q4_K_M·160.4 t/s	Q4_K_M	7.8 GB65%	160.4 t/s	131K	S97, Runs great
II Medical 8B 17068.2BChat Q4_K_M·59.3 t/s	Q4_K_M	7.6 GB64%	59.3 t/s	41K	A84, Runs well
Arete 27B27.4BChatFunctions IQ3_XXS·28.9 t/s	IQ3_XXS	11.8 GB98%	28.9 t/s	262K	C41, Usable
Gemma 3 1B Pt1000MChat Q4_K_M·496.4 t/s	Q4_K_M	2.1 GB17%	496.4 t/s	—	S100, Runs great
OLMoE 1B 7B 09246.9BChat Q4_K_M·281.7 t/s	Q4_K_M	5.0 GB42%	281.7 t/s	4K	S100, Runs great
Llama Guard 3 1B1.5BChat Q4_K_M·330.9 t/s	Q4_K_M	2.6 GB22%	330.9 t/s	—	S100, Runs great

RTX 4070 Ti specs, power and PSU

Specs

Architecture: Ada Lovelace
VRAM: 12 GB GDDR6X
Memory bandwidth: 504.0 GB/s
FP16 (dense): 80.20 TFLOPS
CUDA cores: 7,680
Tensor cores: 240
Compute capability: 8.9
TDP: 285 W
Released: 2023-01-05
MSRP: $799

RTX 4070 Ti FAQ

Is the RTX 4070 Ti still worth it in 2026?

At ≈$722 used you get 7.1 tok/s per $100 on Qwen3.5 9B, which ranks 7th of the 8 cards compared here; it is also the 3rd fastest out of 9 cards with 12 GB. It runs 7–9B models well; 14B only just fits.

What is the largest model the RTX 4070 Ti can run?

GPT OSS 20B (20.9B) is the largest at 4-bit or better: at IQ4_XS it uses 11.8 GB of 12 GB, and runs at about 119 tok/s.

Can the RTX 4070 Ti run Qwen3.5 9B?

Yes. Qwen3.5 9B fits at Q4_K_M, using 6.6 GB of 12 GB, and it is the best model that runs well on this card.

Can the RTX 4070 Ti run 27–31B models?

No. Qwen3.8 27B needs 17.9 GB at Q4, more than the 12 GB on this card.

How many tokens per second does the RTX 4070 Ti give?

About 51.5 tok/s on Qwen3.5 9B at Q4_K_M, with the first token after 2.2 s on a 4K-token prompt.

What power supply does the RTX 4070 Ti need?

Plan a 600 W PSU (2× the 285 W TDP).

Is 12 GB enough for coding and agents?

Yes for coding: Llama 3.1 8B Instruct, the only coding-scored model that fits, runs at about 62 tok/s. For agents, not yet: no agent-scored model fits in less than 96 GB.

Is renting cheaper than buying an RTX 4070 Ti?

Rent from $0.24/hr. Renting costs as much as buying after ≈3,000 hours (≈2.0 years at 4 h a day).

Best coding LLMs 12 GB VRAM 16 GB VRAM GPUs with 12 GB or more RTX 3090 Ti RTX 4090