NVIDIA · Blackwell · 16 GB VRAM tier
Best AI Models for NVIDIA GeForce RTX 5070 Ti (16 GB)
Runs 14B models well; 27–31B only just fits.
| # | Model | Speed | llmrun Score | Quant · VRAM |
|---|---|---|---|---|
| 1 | Qwen3.5 9BAlibabaHow to run → Q4_K_M · 6.6 GB · 91.6 t/s | 91.6 tok/s | Q4_K_M · 6.6 GB | |
| 2 | Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB · 179 t/s | 179 tok/s | Q4_K_M · 3.4 GB | |
| 3 | GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 173 t/s | 173 tok/s | Q4_K_M · 13.1 GB | |
| 4 | Phi 4Microsoft Q4_K_M · 12.5 GB · 61.2 t/s | 61.2 tok/s | Q4_K_M · 12.5 GB | |
| 5 | Gemma 4 12B ITGoogle Q4_K_M · 9.0 GB · 70.8 t/s | 70.8 tok/s | Q4_K_M · 9.0 GB |
| # | Model | Speed | Coding Score | Quant · VRAM |
|---|---|---|---|---|
| 1 | GPT OSS 20BOpenAIHow to run → Q4_K_M · 13.1 GB · 173 t/s | 173 tok/s | Q4_K_M · 13.1 GB | |
| 2 | Q4_K_M · 7.9 GB · 110 t/s | 110 tok/s | Q4_K_M · 7.9 GB | |
| 3 | Qwen3.5 9BAlibaba Q4_K_M · 6.6 GB · 91.6 t/s | 91.6 tok/s | overall | Q4_K_M · 6.6 GB |
| 4 | Gemma 4 12B ITGoogle Q4_K_M · 9.0 GB · 70.8 t/s | 70.8 tok/s | Q4_K_M · 9.0 GB | |
| 5 | Q4_K_M · 6.5 GB · 93.8 t/s | 93.8 tok/s | Q4_K_M · 6.5 GB |
| # | Model | Speed | Reasoning Score | Quant · VRAM |
|---|---|---|---|---|
| 1 | Qwen3.5 9BAlibabaHow to run → Q4_K_M · 6.6 GB · 91.6 t/s | 91.6 tok/s | Q4_K_M · 6.6 GB | |
| 2 | GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 173 t/s | 173 tok/s | Q4_K_M · 13.1 GB | |
| 3 | Qwen3 8BAlibaba Q4_K_M · 7.6 GB · 106 t/s | 106 tok/s | Q4_K_M · 7.6 GB | |
| 4 | Q4_K_M · 7.9 GB · 110 t/s | 110 tok/s | Q4_K_M · 7.9 GB | |
| 5 | Gemma 4 12B ITGoogle Q4_K_M · 9.0 GB · 70.8 t/s | 70.8 tok/s | Q4_K_M · 9.0 GB |
| # | Model | Speed | Long context Score | Quant · VRAM |
|---|---|---|---|---|
| 1 | Qwen3.5 9BAlibabaHow to run → Q4_K_M · 6.6 GB · 91.6 t/s | 91.6 tok/s | Q4_K_M · 6.6 GB | |
| 2 | Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB · 179 t/s | 179 tok/s | Q4_K_M · 3.4 GB | |
| 3 | Mistral Nemo Instruct 2407Mistral AI Q4_K_M · 11.0 GB · 72.2 t/s | 72.2 tok/s | Q4_K_M · 11.0 GB | |
| 4 | Q4_K_M · 7.9 GB · 110 t/s | 110 tok/s | Q4_K_M · 7.9 GB | |
| 5 | Gemma 4 12B ITGoogle Q4_K_M · 9.0 GB · 70.8 t/s | 70.8 tok/s | Q4_K_M · 9.0 GB |
| # | Model | Speed ↓ | llmrun Score | Quant · VRAM |
|---|---|---|---|---|
| 1 | Qwen3.5 4BAlibabaHow to run → Q4_K_M · 3.4 GB · 179 t/s | 179 tok/s | Q4_K_M · 3.4 GB | |
| 2 | GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 173 t/s | 173 tok/s | Q4_K_M · 13.1 GB | |
| 3 | Qwen3.5 9BAlibaba Q4_K_M · 6.6 GB · 91.6 t/s | 91.6 tok/s | Q4_K_M · 6.6 GB | |
| 4 | Gemma 4 12B ITGoogle Q4_K_M · 9.0 GB · 70.8 t/s | 70.8 tok/s | Q4_K_M · 9.0 GB | |
| 5 | Phi 4Microsoft Q4_K_M · 12.5 GB · 61.2 t/s | 61.2 tok/s | Q4_K_M · 12.5 GB |
| # | Model | Speed | Vision Score | Quant · VRAM |
|---|---|---|---|---|
| 1 | Qwen3.5 9BAlibabaHow to run → Q4_K_M · 6.6 GB · 91.6 t/s | 91.6 tok/s | Q4_K_M · 6.6 GB | |
| 2 | Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB · 179 t/s | 179 tok/s | Q4_K_M · 3.4 GB | |
| 3 | Gemma 3 12B ITGoogle Q4_K_M · 10.9 GB · 72.4 t/s | 72.4 tok/s | Q4_K_M · 10.9 GB | |
| 4 | Gemma 3 4B ITGoogle Q4_K_M · 5.0 GB · 205 t/s | 205 tok/s | Q4_K_M · 5.0 GB | |
| 5 | Q4_K_M · 6.5 GB · 93.8 t/s | 93.8 tok/s | Q4_K_M · 6.5 GB |
The RTX 5070 Ti is one of the fastest 16 GB cards: it runs 14B models well. It is the most efficient per watt in its tier, and fair value at ≈$1,170. Blackwell generation, released 2025.
RTX 5070 Ti strengths and weaknesses
Strengths
- Runs 35B MoE models: Qwen3.6 35B A3B at 174 tok/s in 15.7 GB
- Reads long prompts fast: A 4K-token prompt on Qwen3.5 9B starts answering in 2.0 s
Weaknesses
- 70B models don't fit: Llama 3.3 70B Instruct needs 51.3 GB at Q4 vs 16 GB here
- Priced well above MSRP: ≈$1,170 new vs its $749 MSRP (+56%)
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.
| Card | New price | tok/s | tok/s per $100 | tok/s per 100 W |
|---|---|---|---|---|
RTX 507012 GB | about $840 | 68.7 | 8.2 | 27.5 |
RX 7900 XTX24 GB | about $1,130 | 90.6 | 8.0 | 25.5 |
RTX 5070 Ti16 GBBest new value | 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 508016 GB | about $1,690 | 98.1 | 5.8 | 27.3 |
RX 9060 XT 16GB16 GB | about $590 | 30.2 | 5.1 | 18.9 |
RTX 509032 GB | about $5,376 | 183 | 3.4 | 31.8 |
| Card | Used price | tok/s | tok/s per $100 | tok/s per 100 W |
|---|---|---|---|---|
RTX 3060 12GB12 GBBest used value | about $329 | 36.8 | 11.2 | 21.6 |
RX 7900 XTX24 GB | about $1,000 | 90.6 | 9.1 | 25.5 |
RTX 5070 Ti16 GB | about $1,100 | 91.6 | 8.3 | 30.5 |
RTX 3090 Ti24 GB | about $1,600 | 103 | 6.4 | 22.9 |
RTX 309024 GB | about $1,500 | 95.7 | 6.4 | 27.3 |
RX 9060 XT 16GB16 GB | about $480 | 30.2 | 6.3 | 18.9 |
RTX 508016 GB | about $1,640 | 98.1 | 6.0 | 27.3 |
RTX 509032 GB | about $6,400 | 183 | 2.9 | 31.8 |
Cost per token: the RTX 5070 Ti against 12–32 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, new price
- $0.81
- Power
- $0.14
Renting costs as much as buying after ≈7,200 hours (≈4.9 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 5070 Ti, each with the one reason it is worth a look. Speeds on Qwen3.5 9B.
Output speed depends on memory bandwidth (896 GB/s). Grey rows need more than 16 GB.
- 9BQwen3.5 9B · Q4_K_M · 6.6 GB91.6tok/s
- 14BQwen3 14B · Q4_K_M · 11.9 GB61.3tok/s
- 38.9tok/s
- 174tok/s
- 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 1057 models on the RTX 5070 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 |
|---|---|---|---|---|---|---|
LightOnOCR 2 1BVision | Q4_K_M | 1.8 GB | 571.0 t/s | 16K | S100, Runs great | |
Qehwa Pashto LlmChat | Q4_K_M | 5.8 GB | 116.7 t/s | 131K | S94, Runs great | |
| BF16 | 3.4 GB | 292.7 t/s | — | S100, Runs great | ||
| Q4_K_M | 3.1 GB | 292.2 t/s | 4K | S100, Runs great | ||
SmolLM2 70MChatCode | Q4_K_M | 0.5 GB | 1532.6 t/s | 8K | S100, Runs great | |
| Q4_K_M | 7.7 GB | 112.9 t/s | 33K | S94, Runs great | ||
Dots.mocrVision | Q4_K_M | 2.6 GB | 267.2 t/s | 131K | S100, Runs great | |
| Q4_K_M | 0.3 GB | 1878.7 t/s | 8K | S100, Runs great | ||
| Q4_K_M | 10.1 GB | 211.7 t/s | 8K | S100, Runs great | ||
DeepSeek OCR 2Vision | Q4_K_M | 2.8 GB | 465.5 t/s | 8K | S100, Runs great | |
Qwen3 8B 64k Context 2X Josiefied UncensoredChatReasoningFunctions | Q4_K_M | 7.6 GB | 105.5 t/s | 66K | S92, Runs great | |
VulnLLM R 7BChatReasoning | Q4_K_M | 5.8 GB | 116.7 t/s | 33K | S94, Runs great | |
Small Qwen3ForCausalLMChatFunctions | Q4_K_M | 0.3 GB | 1878.7 t/s | 41K | S100, Runs great | |
| Q4_K_M | 2.6 GB | 588.3 t/s | — | S100, Runs great | ||
Vaultgemma 1BChat | BF16 | 3.7 GB | 254.3 t/s | — | S100, Runs great |
Specs
- Architecture
- Blackwell
- VRAM
- 16 GB GDDR7
- Memory bandwidth
- 896.0 GB/s
- FP16 (dense)
- 87.90 TFLOPS
- CUDA cores
- 8,960
- Tensor cores
- 280
- Compute capability
- 10.0
- TDP
- 300 W
- Released
- 2025-02-20
- MSRP
- $749
RTX 5070 Ti FAQ
Is the RTX 5070 Ti still worth it in 2026?
At ≈$1,170 you get 7.8 tok/s per $100 on Qwen3.5 9B, which ranks 3rd of the 8 cards compared here; it is also the 2nd fastest out of 17 cards with 16 GB. It runs 14B models well; 27–31B only just fits.
What is the largest model the RTX 5070 Ti can run?
Gemma 4 26B A4B IT (25.8B) is the largest at 4-bit or better: at Q4_K_S it uses 15.5 GB of 16 GB, and runs at about 164 tok/s. At 3-bit, a bigger model fits too: Gemma 2 27B IT (27.2B) at IQ3_M, 15.0 GB.
Can the RTX 5070 Ti run Qwen3.5 9B?
Yes. Qwen3.5 9B fits at Q4_K_M, using 6.6 GB of 16 GB, and it is the best model that runs well on this card.
Can the RTX 5070 Ti run 70B models?
No. Llama 3.3 70B Instruct needs 51.3 GB at Q4, more than the 16 GB on this card.
How many tokens per second does the RTX 5070 Ti give?
About 91.6 tok/s on Qwen3.5 9B at Q4_K_M, with the first token after 2.0 s on a 4K-token prompt.
What power supply does the RTX 5070 Ti need?
Plan a 600 W PSU (2× the 300 W TDP).
Is 16 GB enough for coding and agents?
Yes for coding: GPT OSS 20B, the best of the 2 coding models that fit, runs at about 173 tok/s. For agents, not yet: no agent-scored model fits in less than 96 GB.
Is renting cheaper than buying an RTX 5070 Ti?
Rent from $0.16/hr. Renting costs as much as buying after ≈7,200 hours (≈4.9 years at 4 h a day).