can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA RTX 3080 (10GB) run Kimi K2.7 (MoE)?

Kimi · See model card · estimated for a 10.0 GB machine at 4K context.

No — too big for this machine.

Kimi K2.7 (MoE) needs more memory than the 10.0 GB on a NVIDIA RTX 3080 (10GB), even at its smallest quantization.

Too big for your machine — run it in the cloud

Needs multi-GPU 80 GB+ (H100 / H200) · about $8–24/hr

  • RunPodPer-second GPU pods — bring your own GGUF, spin up on demand.
  • Vast.aiCheap GPU marketplace — rent by the hour, bring your own GGUF.
  • VultrCloud GPU VMs by the hour — full root access, run any stack.

Affiliate links — we may earn a commission if you sign up, at no cost to you. Prices are indicative and vary by provider and region.

Ran Kimi K2.7 (MoE) on a NVIDIA RTX 3080 (10GB)? Add your real numbers →