NVIDIA · Ampere · 8 GB VRAM tier
Best AI Models for NVIDIA GeForce RTX 3070 Ti (8 GB)
Runs 7–9B models well; 14B doesn't fit in 8 GB.
| # | Model | Speed | llmrun Score | Quant · VRAM |
|---|---|---|---|---|
| 1 | Qwen3.5 9BAlibabaHow to run → Q4_K_M · 6.6 GB · 62.2 t/s | 62.2 tok/s | Q4_K_M · 6.6 GB | |
| 2 | Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB · 121 t/s | 121 tok/s | Q4_K_M · 3.4 GB | |
| 3 | Gemma 2 9B ITGoogle Q4_K_M · 7.3 GB · 64.8 t/s | 64.8 tok/s | Q4_K_M · 7.3 GB | |
| 4 | Gemma 3 4B ITGoogle Q4_K_M · 5.0 GB · 139 t/s | 139 tok/s | Q4_K_M · 5.0 GB | |
| 5 | Ling 3.0 TinyInclusion AI Q4_K_M · 5.5 GB · 271 t/s | 271 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 · 62.2 t/s | 62.2 tok/s | Q4_K_M · 6.6 GB | |
| 2 | Gemma 3 4B ITGoogle Q4_K_M · 5.0 GB · 139 t/s | 139 tok/s | Q4_K_M · 5.0 GB | |
| 3 | Qwen2.5 7B InstructAlibaba Q4_K_M · 5.8 GB · 79.2 t/s | 79.2 tok/s | Q4_K_M · 5.8 GB | |
| 4 | Gemma 2 9B ITGoogle Q4_K_M · 7.3 GB · 64.8 t/s | 64.8 tok/s | overall | Q4_K_M · 7.3 GB |
| 5 | Ling 3.0 TinyInclusion AI Q4_K_M · 5.5 GB · 271 t/s | 271 tok/s | Q4_K_M · 5.5 GB |
| # | Model | Speed | Long context Score | Quant · VRAM |
|---|---|---|---|---|
| 1 | Qwen3.5 4BAlibabaHow to run → Q4_K_M · 3.4 GB · 121 t/s | 121 tok/s | Q4_K_M · 3.4 GB | |
| 2 | Qwen3.5 9BAlibaba Q4_K_M · 6.6 GB · 62.2 t/s | 62.2 tok/s | Q4_K_M · 6.6 GB | |
| 3 | Gemma 4 E4B ITGoogle Q4_K_M · 5.6 GB · 74.3 t/s | 74.3 tok/s | Q4_K_M · 5.6 GB | |
| 4 | Ling 3.0 TinyInclusion AI Q4_K_M · 5.5 GB · 271 t/s | 271 tok/s | Q4_K_M · 5.5 GB | |
| 5 | MiniCPM5 2BOpenBMB Q4_K_M · 2.5 GB · 208 t/s | 208 tok/s | Q4_K_M · 2.5 GB |
| # | Model | Speed ↓ | llmrun Score | Quant · VRAM |
|---|---|---|---|---|
| 1 | Qwen3.5 4BAlibabaHow to run → Q4_K_M · 3.4 GB · 121 t/s | 121 tok/s | Q4_K_M · 3.4 GB | |
| 2 | Ling 3.0 TinyInclusion AI Q4_K_M · 5.5 GB · 271 t/s | 271 tok/s | Q4_K_M · 5.5 GB | |
| 3 | Gemma 4 E4B ITGoogle Q4_K_M · 5.6 GB · 74.3 t/s | 74.3 tok/s | Q4_K_M · 5.6 GB | |
| 4 | Q4_K_M · 6.5 GB · 63.7 t/s | 63.7 tok/s | Q4_K_M · 6.5 GB | |
| 5 | Qwen3.5 9BAlibaba Q4_K_M · 6.6 GB · 62.2 t/s | 62.2 tok/s | Q4_K_M · 6.6 GB |
| # | Model | Speed | Vision Score | Quant · VRAM |
|---|---|---|---|---|
| 1 | Qwen3.5 9BAlibabaHow to run → Q4_K_M · 6.6 GB · 62.2 t/s | 62.2 tok/s | Q4_K_M · 6.6 GB | |
| 2 | Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB · 121 t/s | 121 tok/s | Q4_K_M · 3.4 GB | |
| 3 | Gemma 3 4B ITGoogle Q4_K_M · 5.0 GB · 139 t/s | 139 tok/s | Q4_K_M · 5.0 GB | |
| 4 | Q4_K_M · 6.5 GB · 63.7 t/s | 63.7 tok/s | Q4_K_M · 6.5 GB | |
| 5 | LFM3 Omni 2BLiquid AI Q4_K_M · 2.4 GB · 233 t/s | 233 tok/s | Q4_K_M · 2.4 GB |
The RTX 3070 Ti is the quickest card in the 8 GB class: it runs 7–9B models well. It is more efficient per watt than most 8 GB cards, and at its $599 MSRP it gave the best speed per dollar of the cards compared. Ampere generation, released 2021.
RTX 3070 Ti strengths and weaknesses
Strengths
- Runs 7–9B models: Qwen3.5 9B at 62.2 tok/s in 6.6 GB
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
- No FP8 or NVFP4: Ampere 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 RTX 3070 Ti has no current price, so it is shown at its MSRP.
| Card | New price | tok/s | tok/s per $100 | tok/s per 100 W |
|---|---|---|---|---|
RTX 3070 Ti8 GB | about $599 | 62.2 | 10.4 | 21.4 |
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 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 |
RTX 309024 GB | about $1,500 | 95.7 | 6.4 | 27.3 |
Cost per token: the RTX 3070 Ti against 8–24 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.
- Card, MSRP
- $0.61
- Power
- $0.19
Renting costs as much as buying after ≈3,400 hours (≈2.3 years at 4 h a day).
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
Cards people weigh against the RTX 3070 Ti, each with the one reason it is worth a look. Speeds on Qwen3.5 9B.
Output speed depends on memory bandwidth (608 GB/s). Grey rows need more than 8 GB.
- 9BQwen3.5 9B · Q4_K_M · 6.6 GB62.2tok/s
- 14BQwen3 14B · not at 4-bitneeds 11.9 GB
- 27–31BQwen3.8 27B · not at 4-bitneeds 17.9 GB
- 35B MoEQwen3.6 35B A3B · not at 4-bitneeds 22.0 GB
- 70BLlama 3.3 70B Instruct · not at 4-bitneeds 51.3 GB
- 120B MoEGPT OSS 120B · not at 4-bitneeds 70.8 GB
Estimated speeds: Q4_K_M, 4K context, one user. How we estimate
All 216 models on the RTX 3070 Ti
Featured onlyBest quant that fits, ordered by llmrun Score. Fit grades how well it runs here, S best. How ranking works
| Model | Quant | VRAM | Speed | Context | Score | Fit |
|---|---|---|---|---|---|---|
D1 3BVisionFunctions | Q4_K_M | 2.6 GB | 171.9 t/s | 33K | S98, Runs great | |
NVIDIA Nemotron Labs Dory1.0 4B BF16ChatFunctions | Q4_K_M | 5.7 GB | 129.2 t/s | 262K | S95, Runs great | |
Gemma 4 E2B ITChatFunctions | Q4_K_M | 3.5 GB | 115.3 t/s | 131K | S94, Runs great | |
North Micro Vision InstructVisionChat | Q4_K_M | 3.7 GB | 194.8 t/s | 500K | S99, Runs great | |
WeVisOne VL 2BVisionFunctions | Q4_K_M | 3.6 GB | 197.7 t/s | 262K | S100, Runs great | |
D1 2BVisionFunctions | Q4_K_M | 2.3 GB | 255.1 t/s | 128K | S100, Runs great | |
FrogNano 4B 2609ChatFunctions | Q4_K_M | 3.4 GB | 121.3 t/s | 262K | S95, Runs great | |
Granite Vision 4.1 4BVisionFunctions | Q4_K_M | 4.0 GB | 137.8 t/s | 131K | S96, Runs great | |
WeVisOne VL 4BVisionFunctions | Q4_K_M | 4.7 GB | 116.6 t/s | 262K | S94, Runs great | |
Clef FlashVisionFunctions | Q4_K_M | 6.5 GB | 63.7 t/s | 262K | A83, Runs well | |
MiniCPM V 4.6VisionFunctions | Q4_K_M | 1.5 GB | 349.9 t/s | 262K | S100, Runs great | |
Cosmos Reason2 2BVisionChatReasoningFunctions | Q4_K_M | 3.5 GB | 245.6 t/s | — | S100, Runs great | |
D1 Omni 600MVision | Q4_K_M | 1.2 GB | 549.2 t/s | 128K | S100, Runs great | |
LocateAnything 3BVisionFunctions | Q4_K_M | 3.2 GB | 148.1 t/s | 33K | S97, Runs great | |
MinerU2.5 Pro 2605 1.2BVision | Q4_K_M | 1.1 GB | 387.6 t/s | 8K | S100, Runs great |
Specs
- Architecture
- Ampere
- VRAM
- 8 GB GDDR6X
- Memory bandwidth
- 608.3 GB/s
- FP16 (dense)
- 43.50 TFLOPS
- CUDA cores
- 6,144
- Tensor cores
- 192
- Compute capability
- 8.6
- TDP
- 290 W
- Released
- 2021-06-10
- MSRP
- $599
RTX 3070 Ti FAQ
Is the RTX 3070 Ti still worth it in 2026?
At its MSRP of $599 you get 10.4 tok/s per $100 on Qwen3.5 9B, which ranks 1st of the 4 cards compared here; it is also the 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 3070 Ti 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 62.2 tok/s.
Can the RTX 3070 Ti 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 3070 Ti give?
About 62.2 tok/s on Qwen3.5 9B at Q4_K_M, with the first token after 4.0 s on a 4K-token prompt.
What power supply does the RTX 3070 Ti need?
Plan a 600 W PSU (2× the 290 W TDP).
Is renting cheaper than buying an RTX 3070 Ti?
Rent from $0.18/hr. Renting costs as much as buying after ≈3,400 hours (≈2.3 years at 4 h a day).