NVIDIA GeForce RTX 4060 Ti 16GB
16 GB · 288 GB/s · 165 W
Prices
Every retailer we track in the US, cheapest first. Buy links may earn us a commission.
No retailer in this market lists it right now.
What two of them run
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 3.8 27B Alibaba Qwen | Q8_0 | fits | 28.8 GB | 36k64k with q8 cache | 6tok/sest. | 346 tok/s | – |
| Qwen 3.6 27B Alibaba Qwen | Q8_0 | fits | 28.4 GB | 42k74k with q8 cache | 6tok/sest. | 346 tok/s | – |
| Gemma 4 31B | Q6_K | fits | 26.0 GB | 64k122k with q8 cache | 7tok/sest. | 302 tok/s | – |
| Qwen 3.6 35B-A3B Alibaba Qwen | UD-Q6_K | fits | 28.7 GB | 92k144k with q8 cache | 40tok/sest. | 2968 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 27B Alibaba Qwen | Q8_0 | fits | 28.4 GB | 42k74k with q8 cache | 6tok/sest. | 346 tok/s | – |
| Gemma 4 26B-A4B | Q8_0 | fits | 26.5 GB | 176k256k with q8 cache | 24tok/sest. | 2262 tok/s | chat, coding, long documents |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q6_K | fits | 28.2 GB | 109k170k with q8 cache | 41tok/sest. | 2968 tok/s | chat, coding, agents, long documents |
| GLM 4.7 Flash Z.ai | Q6_K | fits | 24.6 GB | 116k198k with q8 cache | 24tok/sest. | 1661 tok/s | chat |
| Devstral Small 2 24B Mistral AI | Q8_0 | fits | 25.7 GB | 39k71k with q8 cache | 7tok/sest. | 391 tok/s | – |
| Kimi Linear 48B-A3B Moonshot AI | Q4_K_M | fits | 29.2 GB | 122k167k with q8 cache | 55tok/sest. | 2821 tok/s | chat, coding, long documents |
| gpt-oss 20B OpenAI | MXFP4 | fits | 12.6 GB | 128k | 41tok/sest. | 2148 tok/s | chat, coding, agents, long documents |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q6_K | fits | 25.3 GB | 63k113k with q8 cache | 33tok/sest. | 2147 tok/s | chat |
| Qwen3 32B Alibaba Qwen | Q6_K | fits | 28.2 GB | 18k33k with q8 cache | 6tok/sest. | 267 tok/s | – |
| Gemma 4 12B | Q8_0 | fits | 13.4 GB | 256k | 14tok/sest. | 788 tok/s | – |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 10.3 GB | 256k | 18tok/sest. | 998 tok/s | chat |
| Mistral Small 3.2 24B Mistral AI | Q8_0 | fits | 25.7 GB | 39k71k with q8 cache | 7tok/sest. | 391 tok/s | – |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q6_K | fits | 28.2 GB | 18k33k with q8 cache | 6tok/sest. | 279 tok/s | – |
| Gemma 3 27B | Q8_0 | fits | 28.9 GB | 30k58k with q8 cache | 6tok/sest. | 351 tok/s | – |
| Ministral 3 14B Mistral AI | Q8_0 | fits | 15.8 GB | 100k183k with q8 cache | 11tok/sest. | 648 tok/s | – |
| Qwen3 14B Alibaba Qwen | Q8_0 | fits | 17.0 GB | 40k | 11tok/sest. | 602 tok/s | – |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q8_0 | fits | 10.4 GB | 128k | 18tok/sest. | 1053 tok/s | chat |
| Qwen3 8B Alibaba Qwen | Q8_0 | fits | 10.4 GB | 40k | 18tok/sest. | 1053 tok/s | chat |
| Phi-4 14B Microsoft | Q8_0 | fits | 17.2 GB | 16k | 10tok/sest. | 606 tok/s | – |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 5.6 GB | 256k | 37tok/sest. | 2009 tok/s | chat, coding, long documents |
| Ministral 3 8B Mistral AI | Q8_0 | fits | 10.6 GB | 153k256k with q8 cache | 18tok/sest. | 984 tok/s | chat |
| Granite 4.2 8B IBM | Q8_0 | fits | 11.1 GB | 128k | 17tok/sest. | 977 tok/s | chat |
| Gemma 4 E4B | Q8_0 | fits | 9.0 GB | 128k | 21tok/sest. | 1209 tok/s | chat |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 9.9 GB | 125k | 73tok/sest. | 7058 tok/s | chat, coding |
| Llama 3.1 8B Meta | Q6_K | fits | 8.3 GB | 128k | 23tok/sest. | 1087 tok/s | chat |
| Qwen 3.5 122B-A10B Alibaba Qwen | UD-Q2_K_XL | offload | 40.4 GB | – | 19tok/sest. | 781 tok/s | chat |
| Qwen3 Coder Next Alibaba Qwen | Q4_K_M | offload | 46.6 GB | – | 23tok/sest. | 1832 tok/s | chat |
| Nemotron 3 Super 120B-A12B NVIDIA | UD-Q2_K_XL | offload | 52.3 GB | – | 10tok/sest. | 604 tok/s | – |
| Mistral Small 4 119B Mistral AI | UD-Q2_K_XL | offload | 38.8 GB | – | 28tok/sest. | 1045 tok/s | chat, coding |
| GLM 4.5 Air Z.ai | Q2_K | offload | 44.8 GB | – | 7tok/sest. | 369 tok/s | – |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q4_K_M | offload | 46.6 GB | – | 29tok/sest. | 2303 tok/s | chat, coding |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | UD-Q6_K_XL | offload | 33.8 GB | – | 26tok/sest. | 2920 tok/s | chat, coding, long documents |
| Llama 3.3 70B Meta | Q4_K_M | offload | 43.2 GB | – | 2tok/sest. | 107 tok/s | – |
| DeepSeek V4 Flash DeepSeek | UD-Q2_K_XL | won't run | 92.0 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 | 74.9 GB | – | – | – | – |
| MiniMax M2.7 MiniMax | UD-Q2_K_XL | won't run | 73.2 GB | – | – | – | – |
| gpt-oss 120B OpenAI | MXFP4 | won't run | 60.5 GB | – | – | – | – |
Specifications
From the manufacturer's published specifications; sources are linked where we have them.
- GPU
- GeForce RTX 4060 Ti 16GB
- Memory
- 16 GB GDDR6
- Memory bus
- 128-bit
- Memory bandwidth
- 288 GB/s
- FP16 compute
- 44 TFLOPS
- Software
- CUDA
- Board power
- 165 W
- PCIe generation
- Gen 4
- PCIe lanes
- x8