# GeForce RTX 5060 Ti 16 GB

> GDDR7 lifts bandwidth by about half over the 4060 Ti for a similar price.

Canonical: https://thelocalbench.com/hardware/rtx-5060-ti-16g · Data as of 2026-10-12 · The Local Bench (thelocalbench.com), data as of 2026-10-12, CC BY 4.0

Flags: [verified] checked against primary source · [sourced] cited · [estimate] formula · [sample] placeholder

## Specifications

| Field | Value | Flag | Source / note |
|---|---|---|---|
| memory_gb | 16 | sourced | https://www.nvidia.com/en-us/geforce/graphics-cards/50-series/rtx-5060-family/ |
| bandwidth_gbs | 448 | sourced | https://en.wikipedia.org/wiki/GeForce_RTX_50_series |
| fp16_tflops | 47 | sample | Sample FP16 dense compute; pending vendor-sheet citation. |
| load_watts | 250 | sample | Sample wall power under load. |
| price_usd | 779.99 | sourced | https://www.newegg.com/p/pl?d=rtx+5060+ti+16gb&N=4131 |

## Models that run (default quant, 8k)

| Model | Quant | Memory GB | Verdict | Decode tok/s |
|---|---|---|---|---|
| [Llama 3.1 8B Instruct](/models/llama-3.1-8b.md) | Q4_K_M | 6.6 | fit | 44.8 [estimate] |
| [Qwen3 8B](/models/qwen3-8b.md) | Q4_K_M | 6.8 | fit | 43.1 [estimate] |
| [Qwen3 14B](/models/qwen3-14b.md) | Q4_K_M | 10.9 | fit | 26.0 [estimate] |
| [gpt-oss-20b](/models/gpt-oss-20b.md) | MXFP4 | 12.9 | fit | 117.4 [estimate] |
| [Mistral Small 3.2 24B](/models/mistral-small-3.2-24b.md) | Q4_K_M | 16.2 | offload | 12.7 [estimate] |
| [Gemma 3 27B IT](/models/gemma-3-27b.md) | Q4_K_M | 18.2 | offload | 7.1 [estimate] |
| [Qwen3 30B-A3B](/models/qwen3-30b-a3b.md) | Q4_K_M | 19.9 | offload | 42.3 [estimate] |
| [Qwen3 32B](/models/qwen3-32b.md) | Q4_K_M | 22.5 | offload | 3.7 [estimate] |
| [Llama 3.3 70B Instruct](/models/llama-3.3-70b.md) | Q4_K_M | 45.8 | nofit | — |
| [gpt-oss-120b](/models/gpt-oss-120b.md) | MXFP4 | 64.3 | nofit | — |