NVIDIA · Entry

NVIDIA GeForce RTX 2060

NVIDIA GeForce RTX 2060 is a entry-level GPU from NVIDIA. It offers 6 GB of VRAM, suitable for small and heavily quantized models. It delivers 6.45 TFLOPS of FP32 compute performance with 336 GB/s of memory bandwidth It can run 12 models in our database. It's a cost-effective entry point for experimenting with local LLMs.

Specifications

VendorNVIDIA
Full NameNVIDIA GeForce RTX 2060
VRAM6GB
Performance TierEntry
Benchmark Score14,100
FP32 Compute6.45TFLOPS
Memory Bandwidth336GB/s
Compatible Models12Models that can run on this GPU

Strengths

  • 336 GB/s bandwidth — good memory throughput
  • Affordable entry point for trying local LLMs

Limitations

  • 6 GB VRAM — limited to small and heavily quantized models
  • 6.45 TFLOPS — modest compute may limit inference speed
  • Limited future-proofing — may struggle with next-generation models

Compatible Models (12)

FAQ

NVIDIA GeForce RTX 2060 — 规格、兼容模型与 LLM 性能 — LLMFit Web