# GeForce RTX 5060 Ti 16GB

> OnPrem World · https://onpremworld.com/en/hardware/rtx-5060-ti-16gb · Last updated: 2026-10-16 · CC BY 4.0

16 GB of GDDR7 for $429 at launch, with 56% more bandwidth than the RTX 4060 Ti 16GB (448 vs 288 GB/s): an affordable way to run models up to about 24B at 4-bit.

## Specifications

|  |  |
|---|---|
| Memory | 16 GB GDDR7 |
| Memory bandwidth | 448 GB/s |
| Power | 180 W |
| Launch | 2025-04 |
| Launch price | US$429 |
| Architecture | Blackwell |
| Software | CUDA |

## What it can run (16 GB, 8K)

Estimates, not benchmarks. See the methodology.

| Model | Parameters | Best quant | Total | tok/s (est.) |
|---|---|---|---|---|
| Gemma 4 26B A4B IT | 25.2B | Q4_K_M | 15.7 GiB | 107 |
| Mistral Small 3.2 24B Instruct (2506) | 24B | Q4_K_M | 16.0 GiB | 21 |
| Magistral Small 1.2 (2509) | 24B | Q4_K_M | 16.0 GiB | 21 |
| Devstral Small 2 24B Instruct (2512) | 24B | Q4_K_M | 16.0 GiB | 21 |
| gpt-oss-20b | 21B | Q5_K_M | 15.3 GiB | 98 |
| Phi-4 (14B) | 14B | Q6_K | 13.3 GiB | 26 |
| Gemma 3 12B IT | 12B | Q8_0 | 13.8 GiB | 23 |
| Gemma 4 12B Unified IT | 11.95B | Q8_0 | 13.3 GiB | 24 |
| Qwen3.5-9B | 9B | Q8_0 | 10.1 GiB | 31 |
| Qwen3-8B | 8.2B | Q8_0 | 10.1 GiB | 34 |
| DeepSeek-R1-0528-Qwen3-8B | 8.19B | Q8_0 | 10.1 GiB | 34 |
| Llama 3.1 8B Instruct | 8B | Q8_0 | 9.8 GiB | 34 |
| Gemma 4 E4B IT | 8B | Q8_0 | 9.1 GiB | 34 |
| Llama 3.2 3B Instruct | 3.21B | FP16 | 7.7 GiB | 44 |
| Kimi K2.6 | 1000B | Doesn't fit | – | – |
| DeepSeek-R1-0528 (671B) | 671B | Doesn't fit | – | – |
| DeepSeek-V4-Flash | 284B | Doesn't fit | – | – |
| Qwen3.8-Flash-Next | 180B | Doesn't fit | – | – |
| Qwen3.5-122B-A10B | 122B | Doesn't fit | – | – |
| Mistral Small 4 119B (2603) | 119B | Doesn't fit | – | – |
| gpt-oss-120b | 117B | Doesn't fit | – | – |
| Llama 4 Scout 17B-16E Instruct | 109B | Doesn't fit | – | – |
| GLM-4.5-Air | 106B | Doesn't fit | – | – |
| Qwen3-Coder-Next (80B-A3B) | 80B | Doesn't fit | – | – |
| Llama 3.3 70B Instruct | 70B | Doesn't fit | – | – |
| Qwen3.5-35B-A3B | 35B | Doesn't fit | – | – |
| Qwen3.6-35B-A3B | 35B | Doesn't fit | – | – |
| Qwen3-32B | 32.8B | Doesn't fit | – | – |
| DeepSeek-R1-Distill-Qwen-32B | 32.76B | Doesn't fit | – | – |
| Gemma 4 31B IT | 30.7B | Doesn't fit | – | – |
| Qwen3-30B-A3B (2507) | 30.5B | Doesn't fit | – | – |
| Qwen3-Coder-30B-A3B-Instruct | 30.5B | Doesn't fit | – | – |
| GLM-4.7-Flash (30B-A3B) | 30B | Doesn't fit | – | – |
| Qwen3.5-27B | 27B | Doesn't fit | – | – |
| Qwen3.6-27B | 27B | Doesn't fit | – | – |
| Qwen3.8-27B | 27B | Doesn't fit | – | – |
| Gemma 3 27B IT | 27B | Doesn't fit | – | – |

## Prices

Latest price at each shop, as listed on the day we checked.

| Region | Shop | Listing | Price | Per GB | Checked |
|---|---|---|---|---|---|
| Taiwan | 原價屋 CoolPC | ｛INNO3D RTX5060Ti 16GB TWIN X2｝2572MHz/25cm/註四年/雙風扇 (Line on the shop's public price list (no per-product page); list stamped 2026/10/14 15:47) | [NT$24,488](https://www.coolpc.com.tw/evaluate.php) | NT$1,531/GB | 2026-10-14 |
| Taiwan | momo購物網 (欣亞數位 SINYA) | 【SINYA 欣亞數位】PNY RTX 5060 Ti 16G OC/std:2692MHz/雙風扇/獨家五年保 (Third-party store inside momo) | [NT$25,090](https://www.momoshop.com.tw/TP/TP0000223/goodsDetail/TP00002230002696) | NT$1,568/GB | 2026-10-14 |
| US | Newegg | MSI Ventus GeForce RTX 5060 Ti 16GB GDDR7 PCI Express 5.0 x16 (use x8) Graphics Card (RTX 5060 Ti 16G VENTUS 2X OC BLACK PLUS) | [US$789.99](https://www.newegg.com/msi-rtx-5060-ti-16g-ventus-2x-oc-black-plus-geforce-rtx-5060-ti-16gb-graphics-card-double-fans/p/N82E16814137992) | US$49/GB | 2026-10-14 |

Taiwan value: about 57.3 tok/s on Llama 3.1 8B Instruct (Q4_K_M, 8K), or 2.3 tok/s per NT$1,000.

US value: about 57.3 tok/s on Llama 3.1 8B Instruct (Q4_K_M, 8K), or 7.2 tok/s per US$100.

All prices: https://onpremworld.com/en/prices.md

## Frequently asked questions

### Which LLMs can the GeForce RTX 5060 Ti 16GB run?

With 16 GB and an 8K context, the largest models that fit include: Gemma 4 26B A4B IT, Mistral Small 3.2 24B Instruct (2506), Magistral Small 1.2 (2509), Devstral Small 2 24B Instruct (2512), gpt-oss-20b. See the full table below.

### How fast is the GeForce RTX 5060 Ti 16GB for local LLMs?

Generation speed is mostly set by memory bandwidth (448 GB/s). For Llama 3.1 8B Instruct at Q8_0, expect roughly 34 tokens/s; bigger models are slower.

### Can the GeForce RTX 5060 Ti 16GB run 70B models?

Llama 3.3 70B Instruct does not fit on the GeForce RTX 5060 Ti 16GB (16 GB), even at Q4_K_M with an 8K context.

## Sources

- https://www.nvidia.com/en-us/geforce/graphics-cards/50-series/rtx-5060-family/
- https://www.nvidia.com/en-us/geforce/graphics-cards/compare/
- https://nvidianews.nvidia.com/news/nvidia-blackwell-geforce-rtx-arrives-for-every-gamer-starting-at-299
- https://www.profesionalreview.com/2025/04/17/rtx-5060-ti-escalado-pcie-5-0-4-0-y-3-0/