NVIDIA · Ada Lovelace · 12 GB VRAM tier

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

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

12 GB GDDR6X504 GB/s71 TFLOPS FP16220 WAda Lovelace 2024

What LLMs can the RTX 4070 SUPER 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 SUPER →Best quant that fits · speeds estimated on this card

About the RTX 4070 SUPER

The RTX 4070 SUPER is a solid mid-range card in the 12 GB class: it runs 7–9B models well. It is more efficient per watt than most 12 GB cards, and at its $599 MSRP it gave among the best speed per dollar of the cards compared. Ada Lovelace generation, released 2024.

Speed in 12 GB#3504 GB/s

Per watt#40.23 tok/s per W on Qwen3.5 9B (9B params)

Per dollar#28.6 tok/s per $100 on Qwen3.5 9B (9B params)

GenerationAda Lovelacereleased 2024

RTX 4070 SUPER 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 2.5 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

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 SUPER 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 4070 SUPER12 GB	about $599	51.5	8.6	23.4
RTX 507012 GB	about $840	68.7	8.2	27.5
RX 7900 XTX24 GB	about $1,130	90.6	8.0	25.5
RX 907016 GB	about $800	60.4	7.6	27.5
RX 9070 XT16 GB	about $815	60.4	7.4	19.9
RTX 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
RX 907016 GB	about $650	60.4	9.3	27.5
RX 7900 XTX24 GB	about $1,000	90.6	9.1	25.5
RTX 407012 GB	about $575	51.5	9.0	25.8
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
RX 9060 XT 16GB16 GB	about $480	30.2	6.3	18.9

Similar GPUs

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

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

▲ 17% speed▲ 4 GB$800

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

▲ 76% speed▲ 12 GB$1,130

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

▼ 28% speedsame 12 GB$329rent $0.07/hr

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

▼ 41% speed▲ 4 GB$590

43% slower, 8 GBRTX 4060 Ti 8GBNVIDIA · 8 GB · Ada Lovelace

▼ 43% speed▼ 4 GB$399rent $0.15/hr

4 GB more and 14% fasterRX 7800 XTAMD · 16 GB · RDNA 3

▲ 14% speed▲ 4 GB$499

RTX 4070 SUPER 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 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 RTX 4070 SUPER — ranked by Score, recency and Fit
Model	Quant	VRAM	Speed	Context	Fit
LFM2.5 2.6B2.7BChatFunctions Q4_K_M·160.6 t/s	Q4_K_M	2.3 GB19%	160.6 t/s	131K	S97, Runs great
InternVL3 5 8B8.5BVision Q4_K_M·58.2 t/s	Q4_K_M	8.2 GB69%	58.2 t/s	—	A83, Runs well
Tiny Qwen3ForCausalLM Instruct 25071MChatFunctions Q4_K_M·1092.0 t/s	Q4_K_M	0.5 GB4%	1092.0 t/s	262K	S100, Runs great
Beetle Monolingual Humanscale Eng194MChat BF16·761.9 t/s	BF16	0.4 GB4%	761.9 t/s	1K	S100, Runs great
Gemma4 E4b Claims Comparison7.9BChatFunctions Q4_K_M·62.0 t/s	Q4_K_M	5.5 GB46%	62.0 t/s	131K	A84, Runs well
Distil Lfm25 Shellper354MChatFunctions Q4_K_M·564.8 t/s	Q4_K_M	0.8 GB6%	564.8 t/s	128K	S100, Runs great
Kimi K2.6 Eagle3 Mla3.0BChat Q4_K_M·151.0 t/s	Q4_K_M	2.6 GB22%	151.0 t/s	262K	S97, Runs great
Gemma 4 E4B IT Assistant4BChat Q4_K_M·121.3 t/s	Q4_K_M	2.7 GB23%	121.3 t/s	131K	S95, Runs great
SmolVLM2 500M Video Instruct507MVision Q4_K_M·474.8 t/s	Q4_K_M	0.9 GB8%	474.8 t/s	8K	S100, Runs great
LFM2.5 230M230MChatFunctions Q4_K_M·655.2 t/s	Q4_K_M	0.6 GB5%	655.2 t/s	128K	S100, Runs great
Nandi Mini 150M153MChat BF16·520.0 t/s	BF16	0.6 GB5%	520.0 t/s	2K	S100, Runs great
Tiny Phi3ForCausalLM 3.5514984Chat Q4_K_M·1092.0 t/s	Q4_K_M	0.5 GB4%	1092.0 t/s	131K	S100, Runs great
VibeThinker 3B3.1BChatMathCodeReasoning Q4_K_M·146.9 t/s	Q4_K_M	2.8 GB23%	146.9 t/s	131K	S97, Runs great
MiniCPM5 1B1.1BChatFunctions Q4_K_M·330.9 t/s	Q4_K_M	1.3 GB10%	330.9 t/s	131K	S100, Runs great
GLM 4.6V Flash10.3BVisionFunctions Q4_K_M·49.9 t/s	Q4_K_M	7.2 GB60%	49.9 t/s	131K	A79, Runs well

RTX 4070 SUPER specs, power and PSU

Specs

Architecture: Ada Lovelace
VRAM: 12 GB GDDR6X
Memory bandwidth: 504.0 GB/s
FP16 (dense): 71.00 TFLOPS
CUDA cores: 7,168
Tensor cores: 224
Compute capability: 8.9
TDP: 220 W
Released: 2024-01-17
MSRP: $599

RTX 4070 SUPER FAQ

Is the RTX 4070 SUPER still worth it in 2026?

At its MSRP of $599 you get 8.6 tok/s per $100 on Qwen3.5 9B, which ranks 2nd 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 SUPER 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 SUPER 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 SUPER 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 SUPER give?

About 51.5 tok/s on Qwen3.5 9B at Q4_K_M, with the first token after 2.5 s on a 4K-token prompt.

What power supply does the RTX 4070 SUPER need?

Plan a 450 W PSU (2× the 220 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 SUPER?

Rent from $0.10/hr. Renting costs as much as buying after ≈5,800 hours (≈4.0 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