NVIDIA GeForce RTX 4060 Ti 8GB
8 GB · 288 GB/s · 160 W
In short
The NVIDIA GeForce RTX 4060 Ti 8GB has 8 GB of GDDR6 memory with 288 GB/s of bandwidth, which sets how fast it generates text. At 64k context it runs 11 of the 129 open models we track fully in memory; the most capable is Qwen 3.5 4B at Q8_0, at about 27 tok/s (estimated). The NVIDIA GeForce RTX 4060 Ti 8GB is not on sale new in the UK right now; used, it starts at £364 (asking price).
Updated . Speeds are estimates; how they are worked out.
Prices
Every retailer we track in the UK, cheapest first. Buy links may earn us a commission.
| Retailer | Condition | Price | Stock | Checked | Buy |
|---|---|---|---|---|---|
| eBayMSI GeForce RTX 4060Ti Dual OC 8GB GDDR6 PCI-Express Graphics Card | used, asking price | £364+ £6 delivery | In stock | 3 h ago | Buy |
| eBayASUS RTX 4060 Ti DUAL OC 8GB SSD Graphics Card | used, asking price | £370+ £7 delivery | In stock | 3 h ago | Buy |
| eBayUsed GeForce RTX 4060 Ti 8GB on eBay | used, asking price | £379 | In stock | 6 h ago | Buy |
| eBayAsus DUAL RTX4060 Ti OC PCIe4 8GB DDR6 HDMI 3 DP Graphics Card | used, asking price | £379+ £6 delivery | In stock | 3 h ago | Buy |
| eBayZOTAC RTX 4060 Ti 8GB Spider-Man Across The Spider-Verse Edition Graphics Card | used, asking price | £500 | In stock | 3 h ago | Buy |
| eBayASUS TUF Gaming GeForce RTX 4060 Ti OC 8GB GDDR6 Graphics Card | used, asking price | £588+ £9 delivery | In stock | 3 h ago | Buy |
| eBayMSI GeForce RTX 4060 Ti VENTUS 2X BLACK 8G OC GDDR6 Graphics Card | used, asking price | £620 | In stock | 3 h ago | Buy |
Used on eBay: median asking price £379, most between £357 and £508 (11 listings, 2026-11-03). Used price history
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 @64k | Prefill | Good for |
|---|---|---|---|---|---|---|---|
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 7.3 GB | 66k110k with q8 cache | 27tok/sest. | 729 tok/s | chat, coding |
| Qwen2.5 0.5B Alibaba Qwen | Q8_0 | fits | 2.3 GB | 32k | 134tok/sest. | 2608 tok/s | chat, coding, long documents |
| Qwen3.5 0.8B Alibaba Qwen | Q8_0 | fits | 2.6 GB | 256k | 109tok/sest. | 2957 tok/s | chat, coding, agents, long documents |
| Qwen3.5 2B Alibaba Qwen | Q5_K_M | fits | 3.2 GB | 256k | 79tok/sest. | 1612 tok/s | chat, coding, agents, long documents |
| LFM3 1.7B Liquid AI | Q8_0 | fits | 3.6 GB | 256k | 67tok/sest. | 1945 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 1.5B DeepSeek | Q8_0 | fits | 4.6 GB | 128k | 47tok/sest. | 1080 tok/s | chat, coding, long documents |
| MiniCPM5 2B openbmb | Q8_0 | fits | 6.2 GB | 89k128k with q8 cache | 33tok/sest. | 609 tok/s | chat, coding, agents |
| Spark X2.5 4B XHToken | mlx-4bit | fits | 6.2 GB | 93k156k with q8 cache | 32tok/sest. | 748 tok/s | chat, coding, agents, long documents |
| FrogNano 4B 2609 Microsoft | Q6_K | fits | 6.6 GB | 84k140k with q8 cache | 30tok/sest. | 729 tok/s | chat, coding, agents |
| LFM2.5 2.6B Liquid AI | Q6_K | fits | 6.9 GB | 71k125k with q8 cache | 29tok/sest. | 738 tok/s | chat, coding, agents |
| LFM2.5 VL 3B Liquid AI | Q6_K | fits | 6.9 GB | 32k | 29tok/sest. | 694 tok/s | chat, coding, agents |
| Qwen 3.8 27B Alibaba Qwen | UD-Q4_K_M | offload | 20.5 GB | – | 3tok/sest. | 86 tok/s | – |
| Qwen 3.6 27B Alibaba Qwen | Q4_K_M | offload | 20.9 GB | – | 3tok/sest. | 86 tok/s | – |
| Gemma 4 31B | Q4_K_M | offload | 23.9 GB | – | 3tok/sest. | 75 tok/s | – |
| Qwen 3.6 35B-A3B Alibaba Qwen | MXFP4 | offload | 22.6 GB | – | 13tok/sest. | 503 tok/s | chat |
| Qwen 3.5 27B Alibaba Qwen | Q4_K_M | offload | 20.8 GB | – | 3tok/sest. | 86 tok/s | – |
| Gemma 4 26B-A4B | MXFP4 | offload | 17.9 GB | – | 11tok/sest. | 559 tok/s | chat |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q4_K_M | offload | 22.9 GB | – | 13tok/sest. | 501 tok/s | chat |
| GLM 4.7 Flash Z.ai | Q4_K_M | offload | 21.4 GB | – | 6tok/sest. | 254 tok/s | – |
| Devstral Small 2 24B Mistral AI | Q4_K_M | offload | 24.4 GB | – | 3tok/sest. | 80 tok/s | – |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | MXFP4 | offload | 23.1 GB | – | 15tok/sest. | 616 tok/s | chat |
| Kimi Linear 48B-A3B Moonshot AI | Q4_K_M | offload | 29.6 GB | – | 16tok/sest. | 374 tok/s | chat |
| gpt-oss 20B OpenAI | Q4_K_M | offload | 13.4 GB | – | 13tok/sest. | 473 tok/s | chat |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q4_K_M | offload | 24.4 GB | – | 5tok/sest. | 176 tok/s | chat |
| Gemma 4 12B | Q4_K_M | offload | 9.0 GB | – | 14tok/sest. | 302 tok/s | chat |
| Qwen 3.5 9B Alibaba Qwen | Q4_K_M | offload | 8.4 GB | 36k60k with q8 cache | 17tok/sest. | 386 tok/s | chat, coding |
| Gemma 3 27B | Q4_K_M | offload | 21.9 GB | – | 3tok/sest. | 95 tok/s | – |
| Mistral Small 3.2 24B Mistral AI | Q4_K_M | offload | 24.4 GB | – | 3tok/sest. | 80 tok/s | – |
| Ministral 3 14B Mistral AI | Q4_K_M | offload | 18.7 GB | – | 4tok/sest. | 124 tok/s | – |
| Qwen3 14B Alibaba Qwen | Q4_K_M | offload | 19.5 GB | – | 4tok/sest. | 107 tok/s | – |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q4_K_M | offload | 14.8 GB | 13k25k with q8 cache | 5tok/sest. | 188 tok/s | chat |
| Qwen3 8B Alibaba Qwen | Q4_K_M | offload | 14.8 GB | 13k25k with q8 cache | 5tok/sest. | 188 tok/s | chat |
| Phi-4 14B Microsoft | Q4_K_M | offload | 21.9 GB | – | 3tok/sest. | 103 tok/s | – |
| Ministral 3 8B Mistral AI | Q4_K_M | offload | 14.4 GB | 13k24k with q8 cache | 6tok/sest. | 188 tok/s | chat |
| Granite 4.2 8B IBM | Q4_K_M | offload | 16.2 GB | 9k17k with q8 cache | 5tok/sest. | 165 tok/s | chat |
| Gemma 4 E4B | Q4_K_M | offload | 7.5 GB | 61k100k with q8 cache | 25tok/sest. | 546 tok/s | chat, coding |
| LFM2.5 8B-A1B Liquid AI | UD-Q4_K_M | offload | 9.0 GB | 33k56k with q8 cache | 19tok/sest. | 1031 tok/s | chat, coding |
| Llama 3.1 8B Meta | Q4_K_M | offload | 13.7 GB | 16k29k with q8 cache | 6tok/sest. | 210 tok/s | chat |
| Mellum2.1 12B A2.5B Thinking JetBrains | Q4_K_M | offload | 10.2 GB | – | 22tok/sest. | 889 tok/s | chat, coding |
| granite vision 4.1 4b IBM | Q4_K_M | offload | 8.0 GB | 56k100k with q8 cache | 20tok/sest. | 438 tok/s | chat, coding |
| granite 4.2 3b IBM | Q4_K_M | offload | 8.2 GB | 54k95k with q8 cache | 18tok/sest. | 445 tok/s | chat, coding, agents |
| DeepSeek R1 Distill Qwen 7B DeepSeek | Q4_K_M | offload | 8.9 GB | 38k66k with q8 cache | 15tok/sest. | 309 tok/s | chat, coding |
| GLM 4.6V Flash Z.ai | Q4_K_M | offload | 9.3 GB | 21k35k with q8 cache | 13tok/sest. | 203 tok/s | chat, coding |
| Kimi VL A3B Thinking 2506 Moonshot AI | Q4_K_M | offload | 12.8 GB | – | 13tok/sest. | 543 tok/s | chat |
| Ministral 3 3B Instruct 2512 Mistral AI | Q4_K_M | offload | 9.6 GB | 43k78k with q8 cache | 12tok/sest. | 388 tok/s | chat, coding, agents |
| Kimi VL A3B Moonshot AI | mlx-5bit | offload | 14.0 GB | – | 12tok/sest. | 408 tok/s | chat |
| GLM 4 9B 0414 Z.ai | mlx-4bit | offload | 10.2 GB | 2k4k with q8 cache | 11tok/sest. | 202 tok/s | chat |
| LFM2.5 24B A2B Liquid AI | Q4_K_M | offload | 20.4 GB | – | 6tok/sest. | 402 tok/s | chat |
| DeepSeek R1 Distill Llama 8B DeepSeek | Q4_K_M | offload | 13.7 GB | 16k29k with q8 cache | 6tok/sest. | 210 tok/s | chat |
| Ministral 3 8B Reasoning 2512 Mistral AI | Q4_K_M | offload | 14.4 GB | 13k24k with q8 cache | 6tok/sest. | 188 tok/s | chat |
| GLM 4.1V 9B Thinking Z.ai | mlx-8bit | offload | 14.5 GB | – | 6tok/sest. | 161 tok/s | – |
| Muse Glimmer 30B meta-models | Q4_K_M | offload | 18.1 GB | – | 4tok/sest. | 91 tok/s | – |
| Ministral 3 14B Reasoning 2512 Mistral AI | Q4_K_M | offload | 18.7 GB | – | 4tok/sest. | 124 tok/s | – |
| DeepSeek R1 Distill Qwen 14B DeepSeek | Q4_K_M | offload | 21.4 GB | – | 3tok/sest. | 94 tok/s | – |
| Devstral Small 2507 Mistral AI | Q4_K_M | offload | 24.4 GB | – | 3tok/sest. | 81 tok/s | – |
| Magistral Small 2506 Mistral AI | Q4_K_M | offload | 24.4 GB | – | 3tok/sest. | 81 tok/s | – |
| Magistral Small 2507 Mistral AI | Q4_K_M | offload | 24.4 GB | – | 3tok/sest. | 81 tok/s | – |
| Magistral Small 2509 Mistral AI | Q4_K_M | offload | 24.4 GB | – | 3tok/sest. | 80 tok/s | – |
| Qwen3.8 27B OBLITERATED OBLITERATUS | mlx-4bit | offload | 24.5 GB | – | 3tok/sest. | 82 tok/s | – |
| DeepSeek V4 Flash DeepSeek | UD-Q2_K_XL | won't run | 96.6 GB | – | – | – | – |
| GLM 5.3 Flash Z.ai | UD-Q2_K_XL | won't run | 103.1 GB | – | – | – | – |
| Qwen 3.8 Flash Next Alibaba Qwen | UD-Q2_K_XL | won't run | 76.1 GB | – | – | – | – |
| MiniMax M2.7 MiniMax | UD-Q2_K_XL | won't run | 86.7 GB | – | – | – | – |
| Qwen 3.5 122B-A10B Alibaba Qwen | UD-Q2_K_XL | won't run | 41.7 GB | – | – | – | – |
| Nemotron 3 Super 120B-A12B NVIDIA | UD-Q2_K_XL | won't run | 52.6 GB | – | – | – | – |
| Qwen3 Coder Next Alibaba Qwen | Q4_K_M | won't run | 47.8 GB | – | – | – | – |
| gpt-oss 120B OpenAI | Q4_K_M | won't run | 61.8 GB | – | – | – | – |
| Mistral Small 4 119B Mistral AI | UD-Q2_K_XL | won't run | 39.9 GB | – | – | – | – |
| GLM 4.5 Air Z.ai | Q2_K | won't run | 54.8 GB | – | – | – | – |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q4_K_M | won't run | 47.8 GB | – | – | – | – |
| Qwen3 32B Alibaba Qwen | Q4_K_M | won't run | 35.5 GB | – | – | – | – |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q4_K_M | won't run | 35.6 GB | – | – | – | – |
| Llama 3.3 70B Meta | Q4_K_M | won't run | 60.7 GB | – | – | – | – |
| DeepSeek R1 DeepSeek | Q4_K_M | won't run | 382.0 GB | – | – | – | – |
| DeepSeek R1 0528 DeepSeek | Q4_K_M | won't run | 382.5 GB | – | – | – | – |
| DeepSeek R1 Distill Llama 70B DeepSeek | Q4_K_M | won't run | 60.7 GB | – | – | – | – |
| DeepSeek R1 Zero DeepSeek | Q4_K_M | won't run | 382.0 GB | – | – | – | – |
| DeepSeek V3 DeepSeek | Q4_K_M | won't run | 382.0 GB | – | – | – | – |
| DeepSeek V3 0324 DeepSeek | Q4_K_M | won't run | 382.0 GB | – | – | – | – |
| DeepSeek V3.1 DeepSeek | Q4_K_M | won't run | 382.9 GB | – | – | – | – |
| DeepSeek V3.1 Terminus DeepSeek | Q4_K_M | won't run | 382.9 GB | – | – | – | – |
| DeepSeek V3.2 DeepSeek | Q4_K_M | won't run | 382.9 GB | – | – | – | – |
| DeepSeek V4 Flash 0731 DeepSeek | MXFP4 | won't run | 152.1 GB | – | – | – | – |
| DeepSeek V4 Flash Vision Exp DeepSeek | MXFP4 | won't run | 160.9 GB | – | – | – | – |
| Devstral 2 123B Instruct 2512 Mistral AI | Q4_K_M | won't run | 92.8 GB | – | – | – | – |
| GLM 4.5 Z.ai | Q4_K_M | won't run | 225.7 GB | – | – | – | – |
| GLM 4.5V Z.ai | Q4_K_M | won't run | 71.8 GB | – | – | – | – |
| GLM 4.6 Z.ai | Q4_K_M | won't run | 224.9 GB | – | – | – | – |
| GLM 4.6V Z.ai | Q4_K_M | won't run | 78.2 GB | – | – | – | – |
| GLM 4.7 Z.ai | Q4_K_M | won't run | 225.7 GB | – | – | – | – |
| GLM 5 Z.ai | MXFP4 | won't run | 388.9 GB | – | – | – | – |
| GLM 5.1 Z.ai | MXFP4 | won't run | 426.5 GB | – | – | – | – |
| GLM 5.2 Z.ai | UD-Q4_K_M | won't run | 440.4 GB | – | – | – | – |
| GLM 5.3 Z.ai | Q8_0 | won't run | 752.9 GB | – | – | – | – |
| Kimi Dev 72B Moonshot AI | Q6_K | won't run | 81.0 GB | – | – | – | – |
| Kimi K2 Moonshot AI | Q4_K_M | won't run | 583.5 GB | – | – | – | – |
| Kimi K2 Instruct 0905 Moonshot AI | Q4_K_M | won't run | 583.9 GB | – | – | – | – |
| Kimi K2 Thinking Moonshot AI | Q4_K_M | won't run | 583.9 GB | – | – | – | – |
| Kimi K2.5 Moonshot AI | Q4_K_M | won't run | 583.9 GB | – | – | – | – |
| MiniMax M2 MiniMax | Q4_K_M | won't run | 145.4 GB | – | – | – | – |
| MiniMax M2.1 MiniMax | Q4_K_M | won't run | 145.4 GB | – | – | – | – |
| MiniMax M2.5 MiniMax | MXFP4 | won't run | 131.8 GB | – | – | – | – |
| MiniMax M3 MiniMax | MXFP4 | won't run | 248.3 GB | – | – | – | – |
| Mistral Medium 3.5 128B Mistral AI | Q4_K_M | won't run | 92.8 GB | – | – | – | – |
| granite 4.2 30b IBM | Q4_K_M | won't run | 33.9 GB | – | – | – | – |
Specifications
From the manufacturer's published specifications; sources are linked where we have them.
- GPU
- GeForce RTX 4060 Ti 8GB
- Memory
- 8 GB GDDR6
- Memory bus
- 128-bit
- Memory bandwidth
- 288 GB/s
- FP16 compute
- 22.065 TFLOPS
- Software
- CUDA
- Board power
- 160 W
- PCIe generation
- Gen 4
- PCIe lanes
- x8
Compare with
Questions
- How much memory does the NVIDIA GeForce RTX 4060 Ti 8GB have for AI models?
- The NVIDIA GeForce RTX 4060 Ti 8GB has 8 GB of GDDR6 memory with 288 GB/s of bandwidth, which sets how fast it generates text.
- What is the best model the NVIDIA GeForce RTX 4060 Ti 8GB can run locally?
- Qwen 3.5 4B (Q8_0) fits fully in its memory at 64k context and generates at about 27 tok/s, an estimate from its memory bandwidth. 11 of the 129 models we track fit at that context.
- Can the NVIDIA GeForce RTX 4060 Ti 8GB run DeepSeek V4 Flash?
- No: even at UD-Q2_K_XL, DeepSeek V4 Flash needs about 97 GB at 64k context, more than the NVIDIA GeForce RTX 4060 Ti 8GB and system RAM can hold.
- How much does the NVIDIA GeForce RTX 4060 Ti 8GB cost in the UK?
- The NVIDIA GeForce RTX 4060 Ti 8GB is not on sale new in the UK right now; used, it starts at £364 (asking price).
Speeds on this page are for 64k context. See the best hardware for local AI at every budget.