GPU
RTX 4070 Ti SUPER 16GB for local AI
16GB memory, 672 GB/s bandwidth, and deterministic compatibility links for downloadable local models.
- VRAM
- 16GB
- Bandwidth
- 672 GB/s
- Architecture
- Ada Lovelace
- Memory type
- GDDR6X
Models to check on this GPU
- Can it run OpenAI gpt-oss-20b?
- Can it run Google Gemma 3 12B IT?
- Can it run InternVL3 5-GPT-OSS-20B-A4B-Preview?
- Can it run Kimi-VL-A3B-Instruct?
- Can it run Kimi-VL-A3B-Thinking-2506?
- Can it run Moonlight-16B-A3B-Instruct?
- Can it run DeepSeek Coder V2 Lite Instruct?
- Can it run DeepSeek-V2-Lite?
- Can it run DeepSeek R1 Distill Qwen 14B?