GPU

RTX 4060 8GB for local AI

8GB memory, 272 GB/s bandwidth, and deterministic compatibility links for downloadable local models.

VRAM

8GB

Bandwidth

272 GB/s

Architecture

Ada Lovelace

Memory type

GDDR6

Models to check on this GPU

• Can it run Qwen 3.5 4B?
• Can it run Google Gemma 3 4B IT?
• Can it run Qwen 3 32B?
• Can it run Qwen 2.5 Coder 7B Instruct?
• Can it run DeepSeek R1 Distill Qwen 14B?
• Can it run SOLAR-10.7B-v1.0?
• Can it run GLM-4.6V-Flash?
• Can it run Qwen3.5-9B?
• Can it run GLM-4-9B-0414?
• Can it run internlm3-8b-instruct?