NVIDIA GeForce RTX 5060
8 GB · 448 GB/s · 145 W
In short
The NVIDIA GeForce RTX 5060 has 8 GB of GDDR7 memory with 448 GB/s of bandwidth, which sets how fast it generates text. At 32k context it runs 18 of the 129 open models we track fully in memory; the most capable is Qwen 3.5 9B at Q4_K_M, at about 41 tok/s (estimated). The best new price for the NVIDIA GeForce RTX 5060 in the US is $475 at eBay; used, it starts at $448 (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 GeForce RTX 5060 WINDFORCE OC 8G 8GB GDDR7 Graphics Card GPU Dual Fan | used, asking price | $448 | In stock | 4 h ago | Buy |
| eBayASUS DUAL GeForce RTX 5060 8G GDDR7 OC Edition Graphics Card | used, asking price | $450 | In stock | 4 h ago | Buy |
| eBayNEW MSI GeForce RTX 5060 Inspire 2X OC Graphics Card 8GB GDDR7 NVIDIA Blackwell | New | $475 | In stock | 4 h ago | Buy |
| eBayUsed GeForce RTX 5060 on eBay | used, asking price | $480 | In stock | 4 h ago | Buy |
| eBayGIGABYTE GeForce RTX 5060 WINDFORCE MAX OC V2 8G PCI Express 5.0 ATX Graphic Car | New | $482 | In stock | 4 h ago | Buy |
| eBayGIGABYTE GeForce RTX 5060 GAMING OC V2 8G Graphics Card | New | $482 | In stock | 4 h ago | Buy |
| eBayASUS Dual GeForce RTX 5060 OC 8GB GDDR7 PCIe 5.0 DLSS4 HDMI DP Graphics Card NEW | New | $489 | In stock | 4 h ago | Buy |
| eBayGIGABYTE Eagle GeForce RTX 5060 8GB GDDR7 PCI Express 5.0 Graphics Card GV-N5060 | New | $489 | In stock | 4 h ago | Buy |
| eBayGIGABYTE Eagle GeForce RTX 5060 8GB GDDR7 PCI Express 5.0 ATX Graphics Card GV-N | New | $492 | In stock | 4 h ago | Buy |
Used on eBay: median asking price $480, most between $450 and $500 (21 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 @32k | Prefill | Good for |
|---|---|---|---|---|---|---|---|
| Qwen 3.5 9B Alibaba Qwen | Q4_K_M | fits | 7.2 GB | 36k60k with q8 cache | 41tok/sest. | 402 tok/s | chat, coding |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 6.1 GB | 66k110k with q8 cache | 50tok/sest. | 753 tok/s | chat, coding |
| Gemma 4 E4B | Q5_K_M | fits | 6.9 GB | 46k77k with q8 cache | 43tok/sest. | 505 tok/s | chat, coding |
| LFM2.5 8B-A1B Liquid AI | MXFP4 | fits | 7.4 GB | 32k55k with q8 cache | 74tok/sest. | 1653 tok/s | chat, coding |
| Qwen2.5 0.5B Alibaba Qwen | Q8_0 | fits | 1.8 GB | 32k | 298tok/sest. | 3600 tok/s | chat, coding, long documents |
| Qwen3.5 0.8B Alibaba Qwen | Q8_0 | fits | 2.0 GB | 256k | 225tok/sest. | 3381 tok/s | chat, coding, agents, long documents |
| Qwen3.5 2B Alibaba Qwen | Q5_K_M | fits | 2.6 GB | 256k | 150tok/sest. | 1612 tok/s | chat, coding, agents, long documents |
| LFM3 1.7B Liquid AI | Q8_0 | fits | 3.0 GB | 256k | 123tok/sest. | 2007 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 1.5B DeepSeek | Q8_0 | fits | 3.5 GB | 128k | 98tok/sest. | 1354 tok/s | chat, coding, long documents |
| MiniCPM5 2B openbmb | Q8_0 | fits | 4.7 GB | 89k128k with q8 cache | 68tok/sest. | 809 tok/s | chat, coding, agents |
| Spark X2.5 4B XHToken | mlx-4bit | fits | 4.9 GB | 93k156k with q8 cache | 65tok/sest. | 794 tok/s | chat, coding, agents, long documents |
| LFM2.5 2.6B Liquid AI | Q8_0 | fits | 5.4 GB | 62k108k with q8 cache | 57tok/sest. | 916 tok/s | chat, coding, agents |
| LFM2.5 VL 3B Liquid AI | Q8_0 | fits | 5.4 GB | 32k | 57tok/sest. | 840 tok/s | chat, coding, agents |
| FrogNano 4B 2609 Microsoft | Q8_0 | fits | 6.2 GB | 63k104k with q8 cache | 48tok/sest. | 753 tok/s | chat, coding, agents |
| granite vision 4.1 4b IBM | Q8_0 | fits | 6.8 GB | 39k70k with q8 cache | 44tok/sest. | 587 tok/s | chat, coding |
| Ministral 3 3B Instruct 2512 Mistral AI | Q6_K | fits | 6.8 GB | 37k68k with q8 cache | 44tok/sest. | 588 tok/s | chat, coding, agents |
| DeepSeek R1 Distill Qwen 7B DeepSeek | Q4_K_M | fits | 7.0 GB | 38k66k with q8 cache | 42tok/sest. | 396 tok/s | chat, coding |
| granite 4.2 3b IBM | Q8_0 | fits | 7.0 GB | 36k64k with q8 cache | 42tok/sest. | 615 tok/s | chat, coding, agents |
| Qwen 3.8 27B Alibaba Qwen | UD-Q4_K_M | offload | 18.4 GB | – | 4tok/sest. | 87 tok/s | – |
| Qwen 3.6 27B Alibaba Qwen | Q4_K_M | offload | 18.7 GB | – | 4tok/sest. | 86 tok/s | – |
| Gemma 4 31B | Q4_K_M | offload | 21.2 GB | – | 3tok/sest. | 73 tok/s | – |
| Qwen 3.6 35B-A3B Alibaba Qwen | MXFP4 | offload | 21.8 GB | – | 17tok/sest. | 583 tok/s | chat |
| Qwen 3.5 27B Alibaba Qwen | Q4_K_M | offload | 18.6 GB | – | 4tok/sest. | 86 tok/s | – |
| Gemma 4 26B-A4B | MXFP4 | offload | 17.1 GB | – | 14tok/sest. | 566 tok/s | chat |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q4_K_M | offload | 22.1 GB | – | 17tok/sest. | 581 tok/s | chat |
| GLM 4.7 Flash Z.ai | Q4_K_M | offload | 19.6 GB | – | 9tok/sest. | 316 tok/s | – |
| Devstral Small 2 24B Mistral AI | Q4_K_M | offload | 19.2 GB | – | 4tok/sest. | 90 tok/s | – |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | MXFP4 | offload | 22.7 GB | – | 17tok/sest. | 656 tok/s | chat |
| gpt-oss 20B OpenAI | Q4_K_M | offload | 12.5 GB | – | 19tok/sest. | 547 tok/s | chat |
| Kimi Linear 48B-A3B Moonshot AI | Q4_K_M | offload | 29.2 GB | – | 19tok/sest. | 461 tok/s | chat |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q4_K_M | offload | 21.2 GB | – | 9tok/sest. | 271 tok/s | chat |
| Qwen3 32B Alibaba Qwen | Q4_K_M | offload | 27.3 GB | – | 2tok/sest. | 47 tok/s | – |
| Gemma 4 12B | Q4_K_M | offload | 8.3 GB | – | 23tok/sest. | 299 tok/s | chat, coding |
| Gemma 3 27B | Q4_K_M | offload | 19.2 GB | – | 4tok/sest. | 91 tok/s | – |
| Mistral Small 3.2 24B Mistral AI | Q4_K_M | offload | 19.2 GB | – | 4tok/sest. | 90 tok/s | – |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q4_K_M | offload | 27.4 GB | – | 2tok/sest. | 54 tok/s | – |
| Ministral 3 14B Mistral AI | Q4_K_M | offload | 13.6 GB | – | 7tok/sest. | 158 tok/s | – |
| Qwen3 14B Alibaba Qwen | Q4_K_M | offload | 14.3 GB | – | 6tok/sest. | 139 tok/s | – |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q4_K_M | offload | 10.1 GB | 13k25k with q8 cache | 13tok/sest. | 274 tok/s | chat |
| Qwen3 8B Alibaba Qwen | Q4_K_M | offload | 10.1 GB | 13k25k with q8 cache | 13tok/sest. | 274 tok/s | chat |
| Phi-4 14B Microsoft | Q4_K_M | offload | 15.4 GB | – | 5tok/sest. | 135 tok/s | – |
| Ministral 3 8B Mistral AI | Q4_K_M | offload | 10.0 GB | 13k24k with q8 cache | 13tok/sest. | 266 tok/s | chat |
| Granite 4.2 8B IBM | Q4_K_M | offload | 11.0 GB | 9k17k with q8 cache | 10tok/sest. | 239 tok/s | chat |
| Llama 3.1 8B Meta | Q4_K_M | offload | 9.5 GB | 16k29k with q8 cache | 15tok/sest. | 299 tok/s | chat |
| Mellum2.1 12B A2.5B Thinking JetBrains | Q4_K_M | offload | 9.6 GB | – | 35tok/sest. | 1014 tok/s | chat, coding, agents, long documents |
| GLM 4.6V Flash Z.ai | Q4_K_M | offload | 7.9 GB | 21k35k with q8 cache | 29tok/sest. | 264 tok/s | chat, coding |
| Kimi VL A3B Thinking 2506 Moonshot AI | Q4_K_M | offload | 11.7 GB | – | 21tok/sest. | 684 tok/s | chat, coding |
| GLM 4 9B 0414 Z.ai | mlx-4bit | offload | 8.7 GB | 2k4k with q8 cache | 19tok/sest. | 263 tok/s | chat |
| Kimi VL A3B Moonshot AI | mlx-5bit | offload | 12.9 GB | – | 18tok/sest. | 548 tok/s | chat |
| DeepSeek R1 Distill Llama 8B DeepSeek | Q4_K_M | offload | 9.5 GB | 16k29k with q8 cache | 15tok/sest. | 299 tok/s | chat |
| Ministral 3 8B Reasoning 2512 Mistral AI | Q4_K_M | offload | 10.0 GB | 13k24k with q8 cache | 13tok/sest. | 266 tok/s | chat |
| LFM2.5 24B A2B Liquid AI | Q4_K_M | offload | 17.7 GB | – | 12tok/sest. | 583 tok/s | chat |
| GLM 4.1V 9B Thinking Z.ai | mlx-8bit | offload | 13.1 GB | – | 7tok/sest. | 198 tok/s | – |
| Ministral 3 14B Reasoning 2512 Mistral AI | Q4_K_M | offload | 13.6 GB | – | 7tok/sest. | 158 tok/s | – |
| DeepSeek R1 Distill Qwen 14B DeepSeek | Q4_K_M | offload | 15.3 GB | – | 6tok/sest. | 127 tok/s | – |
| Muse Glimmer 30B meta-models | Q4_K_M | offload | 17.5 GB | – | 4tok/sest. | 85 tok/s | – |
| Devstral Small 2507 Mistral AI | Q4_K_M | offload | 19.2 GB | – | 4tok/sest. | 91 tok/s | – |
| Magistral Small 2506 Mistral AI | Q4_K_M | offload | 19.2 GB | – | 4tok/sest. | 91 tok/s | – |
| Magistral Small 2507 Mistral AI | Q4_K_M | offload | 19.2 GB | – | 4tok/sest. | 91 tok/s | – |
| Magistral Small 2509 Mistral AI | Q4_K_M | offload | 19.2 GB | – | 4tok/sest. | 90 tok/s | – |
| Qwen3.8 27B OBLITERATED OBLITERATUS | mlx-4bit | offload | 22.3 GB | – | 3tok/sest. | 81 tok/s | – |
| granite 4.2 30b IBM | Q4_K_M | offload | 25.7 GB | – | 3tok/sest. | 64 tok/s | – |
| DeepSeek V4 Flash DeepSeek | UD-Q2_K_XL | won't run | 93.8 GB | – | – | – | – |
| GLM 5.3 Flash Z.ai | UD-Q2_K_XL | won't run | 102.6 GB | – | – | – | – |
| Qwen 3.8 Flash Next Alibaba Qwen | UD-Q2_K_XL | won't run | 75.2 GB | – | – | – | – |
| MiniMax M2.7 MiniMax | UD-Q2_K_XL | won't run | 78.8 GB | – | – | – | – |
| Qwen 3.5 122B-A10B Alibaba Qwen | UD-Q2_K_XL | won't run | 40.7 GB | – | – | – | – |
| Nemotron 3 Super 120B-A12B NVIDIA | UD-Q2_K_XL | won't run | 52.2 GB | – | – | – | – |
| Qwen3 Coder Next Alibaba Qwen | Q4_K_M | won't run | 46.9 GB | – | – | – | – |
| gpt-oss 120B OpenAI | Q4_K_M | won't run | 60.5 GB | – | – | – | – |
| Mistral Small 4 119B Mistral AI | UD-Q2_K_XL | won't run | 39.0 GB | – | – | – | – |
| GLM 4.5 Air Z.ai | Q2_K | won't run | 48.8 GB | – | – | – | – |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q4_K_M | won't run | 46.9 GB | – | – | – | – |
| Llama 3.3 70B Meta | Q4_K_M | won't run | 50.5 GB | – | – | – | – |
| DeepSeek R1 DeepSeek | Q4_K_M | won't run | 379.7 GB | – | – | – | – |
| DeepSeek R1 0528 DeepSeek | Q4_K_M | won't run | 380.2 GB | – | – | – | – |
| DeepSeek R1 Distill Llama 70B DeepSeek | Q4_K_M | won't run | 50.5 GB | – | – | – | – |
| DeepSeek R1 Zero DeepSeek | Q4_K_M | won't run | 379.7 GB | – | – | – | – |
| DeepSeek V3 DeepSeek | Q4_K_M | won't run | 379.7 GB | – | – | – | – |
| DeepSeek V3 0324 DeepSeek | Q4_K_M | won't run | 379.7 GB | – | – | – | – |
| DeepSeek V3.1 DeepSeek | Q4_K_M | won't run | 380.6 GB | – | – | – | – |
| DeepSeek V3.1 Terminus DeepSeek | Q4_K_M | won't run | 380.6 GB | – | – | – | – |
| DeepSeek V3.2 DeepSeek | Q4_K_M | won't run | 380.6 GB | – | – | – | – |
| DeepSeek V4 Flash 0731 DeepSeek | MXFP4 | won't run | 149.2 GB | – | – | – | – |
| DeepSeek V4 Flash Vision Exp DeepSeek | MXFP4 | won't run | 158.0 GB | – | – | – | – |
| Devstral 2 123B Instruct 2512 Mistral AI | Q4_K_M | won't run | 81.6 GB | – | – | – | – |
| GLM 4.5 Z.ai | Q4_K_M | won't run | 214.0 GB | – | – | – | – |
| GLM 4.5V Z.ai | Q4_K_M | won't run | 65.9 GB | – | – | – | – |
| GLM 4.6 Z.ai | Q4_K_M | won't run | 213.2 GB | – | – | – | – |
| GLM 4.6V Z.ai | Q4_K_M | won't run | 72.2 GB | – | – | – | – |
| GLM 4.7 Z.ai | Q4_K_M | won't run | 214.0 GB | – | – | – | – |
| GLM 5 Z.ai | MXFP4 | won't run | 386.0 GB | – | – | – | – |
| GLM 5.1 Z.ai | MXFP4 | won't run | 423.6 GB | – | – | – | – |
| GLM 5.2 Z.ai | UD-Q4_K_M | won't run | 437.5 GB | – | – | – | – |
| GLM 5.3 Z.ai | Q8_0 | won't run | 750.0 GB | – | – | – | – |
| Kimi Dev 72B Moonshot AI | Q6_K | won't run | 70.8 GB | – | – | – | – |
| Kimi K2 Moonshot AI | Q4_K_M | won't run | 581.2 GB | – | – | – | – |
| Kimi K2 Instruct 0905 Moonshot AI | Q4_K_M | won't run | 581.6 GB | – | – | – | – |
| Kimi K2 Thinking Moonshot AI | Q4_K_M | won't run | 581.6 GB | – | – | – | – |
| Kimi K2.5 Moonshot AI | Q4_K_M | won't run | 581.6 GB | – | – | – | – |
| MiniMax M2 MiniMax | Q4_K_M | won't run | 137.5 GB | – | – | – | – |
| MiniMax M2.1 MiniMax | Q4_K_M | won't run | 137.5 GB | – | – | – | – |
| MiniMax M2.5 MiniMax | MXFP4 | won't run | 123.9 GB | – | – | – | – |
| MiniMax M3 MiniMax | MXFP4 | won't run | 244.3 GB | – | – | – | – |
| Mistral Medium 3.5 128B Mistral AI | Q4_K_M | won't run | 81.6 GB | – | – | – | – |
Specifications
From the manufacturer's published specifications; sources are linked where we have them.
- GPU
- GeForce RTX 5060
- Memory
- 8 GB GDDR7
- Memory bus
- 128-bit
- Memory bandwidth
- 448 GB/s
- FP16 compute
- 19.177 TFLOPS
- Software
- CUDA
- Board power
- 145 W
- PCIe generation
- Gen 5
- PCIe lanes
- x8
Compare with
Questions
- How much memory does the NVIDIA GeForce RTX 5060 have for AI models?
- The NVIDIA GeForce RTX 5060 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 can run locally?
- Qwen 3.5 9B (Q4_K_M) fits fully in its memory at 32k context and generates at about 41 tok/s, an estimate from its memory bandwidth. 18 of the 129 models we track fit at that context.
- Can the NVIDIA GeForce RTX 5060 run DeepSeek V4 Flash?
- No: even at UD-Q2_K_XL, DeepSeek V4 Flash needs about 94 GB at 32k context, more than the NVIDIA GeForce RTX 5060 and system RAM can hold.
- How much does the NVIDIA GeForce RTX 5060 cost in the US?
- The best new price for the NVIDIA GeForce RTX 5060 in the US is $475 at eBay; used, it starts at $448 (asking price).
Speeds on this page are for 32k context. See the best hardware for local AI at every budget.