NVIDIA GeForce RTX 5060 Ti 8GB
8 GB · 448 GB/s · 180 W
In short
The NVIDIA GeForce RTX 5060 Ti 8GB has 8 GB of GDDR7 memory with 448 GB/s of bandwidth, which sets how fast it generates text. At 8k context it runs 26 of the 129 open models we track fully in memory; the most capable is Qwen 3.5 9B at Q5_K_M, at about 40 tok/s (estimated). The best new price for the NVIDIA GeForce RTX 5060 Ti 8GB in the US is $510 at eBay; used, it starts at $450 (asking price).
Updated . Speeds are estimates; how they are worked out.
Prices
Every retailer we track in the US, cheapest first. Buy links may earn us a commission.
| Retailer | Condition | Price | Stock | Checked | Buy |
|---|---|---|---|---|---|
| eBayGigabyte NVIDIA GeForce RTX 5060 Ti Windforce Overclocked Dual Fan 8GB GDDR7 | used, asking price | $450+ $13 delivery | In stock | 5 h ago | Buy |
| eBayASUS Prime NVIDIA GeForce RTX 5060 Ti 8GB | used, asking price | $475 | In stock | 5 h ago | Buy |
| eBayPNY NVIDIA GeForce RTX 5060 Ti 8GB GDDR7 PCIe 5.0 RGB Graphics Card | used, asking price | $499 | In stock | 5 h ago | Buy |
| eBayGIGABYTE Eagle GeForce RTX 5060 Ti 8GB GDDR7 | used, asking price | $480+ $20 delivery | In stock | 5 h ago | Buy |
| eBayPNY GeForce RTX 5060 Ti 8GB GDDR7 Dual Fan Graphics Card PCIe 5.0 Tested | used, asking price | $500 | In stock | 5 h ago | Buy |
| eBayMSI Gaming RTX 5060 Ti 8G Ventus 2X OC Plus Graphics Card GDDR7 | used, asking price | $510 | In stock | 5 h ago | Buy |
| eBayMSI GeForce RTX 5060 TI 8GB GDDR7 SHADOW 2X OC PLUS Video Graphics Card WARRANTY | refurbished | $518 | In stock | 5 h ago | Buy |
| eBayGigabyte NVIDIA GeForce RTX 5060 Ti Windforce Overclocked Dual Fan 8GB GDDR7 | New | $510+ $10 delivery | In stock | 5 h ago | Buy |
| eBayGigabyte GeForce RTX 5060 Ti Windforce MAX EDITION OC 8GB GV-N506TWF2MAX OC-8GD | used, asking price | $520 | In stock | 5 h ago | Buy |
| eBayZOTAC GAMING GeForce RTX 5060 Ti Twin Edge OC 8GB GDDR7 Ray Tracing | used, asking price | $475+ $45 delivery | In stock | 5 h ago | Buy |
| eBayGigabyte GeForce RTX 5060 Ti 8GB GDDR7 Graphics Card 9VN506TW8-00-G10 | used, asking price | $522 | In stock | 5 h ago | Buy |
| eBayUsed GeForce RTX 5060 Ti 8GB on eBay | used, asking price | $530 | In stock | 5 h ago | Buy |
| eBayPNY NVIDIA GeForce RTX 5060 Ti OC 8GB GDDR7 PCIe 5.0 | New | $530 | In stock | 5 h ago | Buy |
| eBayNEW MSI GeForce RTX 5060 Ti 8GB Ventus 2X OC Plus GDDR7 Gaming Graphics Card | New | $535 | In stock | 5 h ago | Buy |
| eBayMSI Gaming NVIDIA RTX 5060Ti 8gb NEW | New | $550 | In stock | 5 h ago | Buy |
| eBayNew ASUS PRIME RTX 5060 Ti OC Overclocked 8GB GDDR7 PRIME-RTX5060TI-O8G SFF | New | $552 | In stock | 5 h ago | Buy |
| eBayGIGABYTE WindForce GeForce RTX 5060 Ti 8GB GDDR7 PCI Express 5.0 x8 ATX Graphics | New | $555 | In stock | 5 h ago | Buy |
| eBayGIGABYTE Eagle GeForce RTX 5060 Ti 8GB GDDR7 PCI Express 5.0 ATX Graphics Card G | New | $555 | In stock | 5 h ago | Buy |
| eBayGIGABYTE Eagle GeForce RTX 5060 Ti 8GB GDDR7 PCI Express 5.0 x8 ATX Graphics Car | New | $565 | In stock | 5 h ago | Buy |
| eBayGIGABYTE Eagle GeForce RTX 5060 Ti 8GB GDDR7 PCI Express 5.0 x8 ATX Graphics Car | New | $565 | In stock | 5 h ago | Buy |
| eBayZOTAC ZTB50610H10A GeForce RTX 5060 Ti Twin Edge OC 8GB GDDR7 Graphics Card NEW | New | $570 | In stock | 5 h ago | Buy |
| eBayASUS Dual GeForce RTX 5060 Ti 8GB GDDR7 PCI Express 5.0 x8 ATX Graphics Card DUA | New | $574 | In stock | 5 h ago | Buy |
Used on eBay: median asking price $530, most between $500 and $580 (23 listings, 2026-11-03). Used price history
Price history
Lowest price shown each day over the last 90 days.
Not enough price history yet.
What it runs
Every model in the catalogue, with the best quant for this hardware. Estimates, not measurements.
| Model | Quant | Fits | Memory | Max context | Decode @8k | Prefill | Good for |
|---|---|---|---|---|---|---|---|
| Qwen 3.5 9B Alibaba Qwen | Q5_K_M | fits | 7.2 GB | 14k23k with q8 cache | 40tok/sest. | 538 tok/s | chat, coding |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q5_K_M | fits | 7.3 GB | 8k15k with q8 cache | 39tok/sest. | 568 tok/s | chat |
| Qwen3 8B Alibaba Qwen | Q5_K_M | fits | 7.3 GB | 8k15k with q8 cache | 39tok/sest. | 568 tok/s | chat |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 5.2 GB | 66k110k with q8 cache | 58tok/sest. | 1082 tok/s | chat, coding |
| Ministral 3 8B Mistral AI | Q4_K_M | fits | 6.7 GB | 13k24k with q8 cache | 44tok/sest. | 530 tok/s | chat |
| Granite 4.2 8B IBM | Q4_K_M | fits | 7.2 GB | 9k17k with q8 cache | 40tok/sest. | 526 tok/s | chat |
| Gemma 4 E4B | Q5_K_M | fits | 6.1 GB | 46k77k with q8 cache | 48tok/sest. | 651 tok/s | chat, coding |
| LFM2.5 8B-A1B Liquid AI | UD-Q5_K_M | fits | 7.0 GB | 14k25k with q8 cache | 144tok/sest. | 3802 tok/s | chat, coding |
| Llama 3.1 8B Meta | Q5_K_M | fits | 7.1 GB | 10k18k with q8 cache | 41tok/sest. | 586 tok/s | chat |
| Qwen2.5 0.5B Alibaba Qwen | Q8_0 | fits | 1.3 GB | 32k | 440tok/sest. | 7958 tok/s | chat, coding, long documents |
| Qwen3.5 0.8B Alibaba Qwen | Q8_0 | fits | 1.6 GB | 256k | 298tok/sest. | 5475 tok/s | chat, coding, agents, long documents |
| Qwen3.5 2B Alibaba Qwen | Q5_K_M | fits | 2.2 GB | 256k | 179tok/sest. | 2246 tok/s | chat, coding, agents, long documents |
| LFM3 1.7B Liquid AI | Q8_0 | fits | 2.6 GB | 256k | 142tok/sest. | 2886 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 1.5B DeepSeek | Q8_0 | fits | 2.7 GB | 128k | 130tok/sest. | 2505 tok/s | chat, coding, long documents |
| MiniCPM5 2B openbmb | Q8_0 | fits | 3.6 GB | 89k128k with q8 cache | 92tok/sest. | 1656 tok/s | chat, coding, agents, long documents |
| LFM2.5 2.6B Liquid AI | Q8_0 | fits | 3.9 GB | 62k108k with q8 cache | 82tok/sest. | 1666 tok/s | chat, coding, agents |
| LFM2.5 VL 3B Liquid AI | Q8_0 | fits | 3.9 GB | 32k | 82tok/sest. | 1471 tok/s | chat, coding, agents |
| Spark X2.5 4B XHToken | mlx-4bit | fits | 3.9 GB | 93k156k with q8 cache | 82tok/sest. | 1178 tok/s | chat, coding, agents, long documents |
| granite vision 4.1 4b IBM | Q8_0 | fits | 4.7 GB | 39k70k with q8 cache | 65tok/sest. | 1103 tok/s | chat, coding |
| Ministral 3 3B Instruct 2512 Mistral AI | Q8_0 | fits | 5.0 GB | 30k55k with q8 cache | 61tok/sest. | 1130 tok/s | chat, coding, agents |
| granite 4.2 3b IBM | Q8_0 | fits | 5.0 GB | 36k64k with q8 cache | 61tok/sest. | 1186 tok/s | chat, coding, agents |
| FrogNano 4B 2609 Microsoft | Q8_0 | fits | 5.3 GB | 63k104k with q8 cache | 56tok/sest. | 1082 tok/s | chat, coding, agents |
| Ministral 3 8B Reasoning 2512 Mistral AI | Q4_K_M | fits | 6.7 GB | 13k24k with q8 cache | 44tok/sest. | 530 tok/s | chat |
| GLM 4.6V Flash Z.ai | Q4_K_M | fits | 6.8 GB | 21k35k with q8 cache | 43tok/sest. | 458 tok/s | chat, coding |
| DeepSeek R1 Distill Qwen 7B DeepSeek | Q6_K | fits | 7.0 GB | 14k25k with q8 cache | 41tok/sest. | 632 tok/s | chat, coding |
| DeepSeek R1 Distill Llama 8B DeepSeek | Q5_K_M | fits | 7.1 GB | 10k18k with q8 cache | 41tok/sest. | 586 tok/s | chat |
| Qwen 3.8 27B Alibaba Qwen | UD-Q4_K_M | offload | 16.7 GB | – | 5tok/sest. | 121 tok/s | – |
| Qwen 3.6 27B Alibaba Qwen | Q4_K_M | offload | 17.0 GB | – | 5tok/sest. | 120 tok/s | – |
| Gemma 4 31B | Q4_K_M | offload | 19.2 GB | – | 4tok/sest. | 100 tok/s | – |
| Qwen 3.6 35B-A3B Alibaba Qwen | MXFP4 | offload | 21.2 GB | – | 21tok/sest. | 952 tok/s | chat |
| Qwen 3.5 27B Alibaba Qwen | Q4_K_M | offload | 17.0 GB | – | 5tok/sest. | 121 tok/s | – |
| Gemma 4 26B-A4B | MXFP4 | offload | 16.5 GB | – | 17tok/sest. | 796 tok/s | chat |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q4_K_M | offload | 21.5 GB | – | 21tok/sest. | 948 tok/s | chat |
| GLM 4.7 Flash Z.ai | Q4_K_M | offload | 18.2 GB | – | 13tok/sest. | 562 tok/s | – |
| Devstral Small 2 24B Mistral AI | Q4_K_M | offload | 15.3 GB | – | 5tok/sest. | 142 tok/s | – |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | MXFP4 | offload | 22.5 GB | – | 19tok/sest. | 973 tok/s | chat |
| gpt-oss 20B OpenAI | Q4_K_M | offload | 11.8 GB | – | 25tok/sest. | 882 tok/s | chat |
| Kimi Linear 48B-A3B Moonshot AI | Q4_K_M | offload | 28.8 GB | – | 21tok/sest. | 824 tok/s | chat |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q4_K_M | offload | 18.8 GB | – | 18tok/sest. | 719 tok/s | chat |
| Qwen3 32B Alibaba Qwen | Q4_K_M | offload | 21.2 GB | – | 3tok/sest. | 86 tok/s | – |
| Gemma 4 12B | Q4_K_M | offload | 7.8 GB | – | 29tok/sest. | 410 tok/s | chat, coding |
| Mistral Small 3.2 24B Mistral AI | Q4_K_M | offload | 15.3 GB | – | 5tok/sest. | 142 tok/s | – |
| Gemma 3 27B | Q4_K_M | offload | 17.2 GB | – | 5tok/sest. | 122 tok/s | – |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q4_K_M | offload | 21.2 GB | – | 3tok/sest. | 90 tok/s | – |
| Ministral 3 14B Mistral AI | Q4_K_M | offload | 9.7 GB | – | 14tok/sest. | 296 tok/s | – |
| Qwen3 14B Alibaba Qwen | Q4_K_M | offload | 10.4 GB | – | 12tok/sest. | 264 tok/s | – |
| Phi-4 14B Microsoft | Q4_K_M | offload | 10.6 GB | – | 11tok/sest. | 263 tok/s | – |
| Mellum2.1 12B A2.5B Thinking JetBrains | Q4_K_M | offload | 9.1 GB | – | 46tok/sest. | 1607 tok/s | chat, coding, agents, long documents |
| GLM 4 9B 0414 Z.ai | mlx-4bit | offload | 7.6 GB | 2k4k with q8 cache | 33tok/sest. | 486 tok/s | chat |
| Kimi VL A3B Thinking 2506 Moonshot AI | Q4_K_M | offload | 10.8 GB | – | 32tok/sest. | 1231 tok/s | chat, coding |
| LFM2.5 24B A2B Liquid AI | Q4_K_M | offload | 15.7 GB | – | 26tok/sest. | 1333 tok/s | chat |
| Kimi VL A3B Moonshot AI | mlx-5bit | offload | 12.0 GB | – | 26tok/sest. | 1094 tok/s | chat |
| Ministral 3 14B Reasoning 2512 Mistral AI | Q4_K_M | offload | 9.7 GB | – | 14tok/sest. | 296 tok/s | – |
| DeepSeek R1 Distill Qwen 14B DeepSeek | Q4_K_M | offload | 10.6 GB | – | 11tok/sest. | 256 tok/s | – |
| GLM 4.1V 9B Thinking Z.ai | mlx-8bit | offload | 12.0 GB | – | 9tok/sest. | 346 tok/s | – |
| Devstral Small 2507 Mistral AI | Q4_K_M | offload | 15.3 GB | – | 5tok/sest. | 144 tok/s | – |
| Magistral Small 2506 Mistral AI | Q4_K_M | offload | 15.3 GB | – | 5tok/sest. | 144 tok/s | – |
| Magistral Small 2507 Mistral AI | Q4_K_M | offload | 15.3 GB | – | 5tok/sest. | 144 tok/s | – |
| Magistral Small 2509 Mistral AI | Q4_K_M | offload | 15.3 GB | – | 5tok/sest. | 142 tok/s | – |
| Muse Glimmer 30B meta-models | Q4_K_M | offload | 17.0 GB | – | 5tok/sest. | 111 tok/s | – |
| granite 4.2 30b IBM | Q4_K_M | offload | 19.5 GB | – | 4tok/sest. | 104 tok/s | – |
| Qwen3.8 27B OBLITERATED OBLITERATUS | mlx-4bit | offload | 20.6 GB | – | 3tok/sest. | 112 tok/s | – |
| DeepSeek V4 Flash DeepSeek | UD-Q2_K_XL | won't run | 91.6 GB | – | – | – | – |
| GLM 5.3 Flash Z.ai | UD-Q2_K_XL | won't run | 102.2 GB | – | – | – | – |
| Qwen 3.8 Flash Next Alibaba Qwen | UD-Q2_K_XL | won't run | 74.5 GB | – | – | – | – |
| MiniMax M2.7 MiniMax | UD-Q2_K_XL | won't run | 72.8 GB | – | – | – | – |
| Qwen 3.5 122B-A10B Alibaba Qwen | UD-Q2_K_XL | won't run | 40.0 GB | – | – | – | – |
| Nemotron 3 Super 120B-A12B NVIDIA | UD-Q2_K_XL | won't run | 51.9 GB | – | – | – | – |
| Qwen3 Coder Next Alibaba Qwen | Q4_K_M | won't run | 46.2 GB | – | – | – | – |
| gpt-oss 120B OpenAI | Q4_K_M | won't run | 59.5 GB | – | – | – | – |
| Mistral Small 4 119B Mistral AI | UD-Q2_K_XL | won't run | 38.4 GB | – | – | – | – |
| GLM 4.5 Air Z.ai | Q2_K | won't run | 44.4 GB | – | – | – | – |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q4_K_M | won't run | 46.2 GB | – | – | – | – |
| Llama 3.3 70B Meta | Q4_K_M | won't run | 42.8 GB | – | – | – | – |
| DeepSeek R1 DeepSeek | Q4_K_M | won't run | 377.9 GB | – | – | – | – |
| DeepSeek R1 0528 DeepSeek | Q4_K_M | won't run | 378.4 GB | – | – | – | – |
| DeepSeek R1 Distill Llama 70B DeepSeek | Q4_K_M | won't run | 42.8 GB | – | – | – | – |
| DeepSeek R1 Zero DeepSeek | Q4_K_M | won't run | 377.9 GB | – | – | – | – |
| DeepSeek V3 DeepSeek | Q4_K_M | won't run | 377.9 GB | – | – | – | – |
| DeepSeek V3 0324 DeepSeek | Q4_K_M | won't run | 377.9 GB | – | – | – | – |
| DeepSeek V3.1 DeepSeek | Q4_K_M | won't run | 378.8 GB | – | – | – | – |
| DeepSeek V3.1 Terminus DeepSeek | Q4_K_M | won't run | 378.8 GB | – | – | – | – |
| DeepSeek V3.2 DeepSeek | Q4_K_M | won't run | 378.8 GB | – | – | – | – |
| DeepSeek V4 Flash 0731 DeepSeek | MXFP4 | won't run | 147.1 GB | – | – | – | – |
| DeepSeek V4 Flash Vision Exp DeepSeek | MXFP4 | won't run | 155.8 GB | – | – | – | – |
| Devstral 2 123B Instruct 2512 Mistral AI | Q4_K_M | won't run | 73.3 GB | – | – | – | – |
| GLM 4.5 Z.ai | Q4_K_M | won't run | 205.2 GB | – | – | – | – |
| GLM 4.5V Z.ai | Q4_K_M | won't run | 61.4 GB | – | – | – | – |
| GLM 4.6 Z.ai | Q4_K_M | won't run | 204.4 GB | – | – | – | – |
| GLM 4.6V Z.ai | Q4_K_M | won't run | 67.8 GB | – | – | – | – |
| GLM 4.7 Z.ai | Q4_K_M | won't run | 205.2 GB | – | – | – | – |
| GLM 5 Z.ai | MXFP4 | won't run | 383.8 GB | – | – | – | – |
| GLM 5.1 Z.ai | MXFP4 | won't run | 421.4 GB | – | – | – | – |
| GLM 5.2 Z.ai | UD-Q4_K_M | won't run | 435.3 GB | – | – | – | – |
| GLM 5.3 Z.ai | Q8_0 | won't run | 747.8 GB | – | – | – | – |
| Kimi Dev 72B Moonshot AI | Q6_K | won't run | 63.2 GB | – | – | – | – |
| Kimi K2 Moonshot AI | Q4_K_M | won't run | 579.4 GB | – | – | – | – |
| Kimi K2 Instruct 0905 Moonshot AI | Q4_K_M | won't run | 579.9 GB | – | – | – | – |
| Kimi K2 Thinking Moonshot AI | Q4_K_M | won't run | 579.9 GB | – | – | – | – |
| Kimi K2.5 Moonshot AI | Q4_K_M | won't run | 579.9 GB | – | – | – | – |
| MiniMax M2 MiniMax | Q4_K_M | won't run | 131.5 GB | – | – | – | – |
| MiniMax M2.1 MiniMax | Q4_K_M | won't run | 131.5 GB | – | – | – | – |
| MiniMax M2.5 MiniMax | MXFP4 | won't run | 118.0 GB | – | – | – | – |
| MiniMax M3 MiniMax | MXFP4 | won't run | 241.4 GB | – | – | – | – |
| Mistral Medium 3.5 128B Mistral AI | Q4_K_M | won't run | 73.3 GB | – | – | – | – |
Specifications
From the manufacturer's published specifications; sources are linked where we have them.
- GPU
- GeForce RTX 5060 Ti 8GB
- Memory
- 8 GB GDDR7
- Memory bus
- 128-bit
- Memory bandwidth
- 448 GB/s
- FP16 compute
- 23.704 TFLOPS
- Software
- CUDA
- Board power
- 180 W
- PCIe generation
- Gen 5
- PCIe lanes
- x8
Compare with
Questions
- How much memory does the NVIDIA GeForce RTX 5060 Ti 8GB have for AI models?
- The NVIDIA GeForce RTX 5060 Ti 8GB has 8 GB of GDDR7 memory with 448 GB/s of bandwidth, which sets how fast it generates text.
- What is the best model the NVIDIA GeForce RTX 5060 Ti 8GB can run locally?
- Qwen 3.5 9B (Q5_K_M) fits fully in its memory at 8k context and generates at about 40 tok/s, an estimate from its memory bandwidth. 26 of the 129 models we track fit at that context.
- Can the NVIDIA GeForce RTX 5060 Ti 8GB run DeepSeek V4 Flash?
- No: even at UD-Q2_K_XL, DeepSeek V4 Flash needs about 92 GB at 8k context, more than the NVIDIA GeForce RTX 5060 Ti 8GB and system RAM can hold.
- How much does the NVIDIA GeForce RTX 5060 Ti 8GB cost in the US?
- The best new price for the NVIDIA GeForce RTX 5060 Ti 8GB in the US is $510 at eBay; used, it starts at $450 (asking price).
Speeds on this page are for 8k context. See the best hardware for local AI at every budget.