Tesla V100-SXM2 32GB
AI overview
Sign in and the AI will write an overview from our coverage.
Headlines · 1
- Lawyer Runs DeepSeek V4.1 Flash on Eight Used Tesla V100 GPUs
A lawyer reportedly built an in-office AI server from eight used 2018-era Nvidia Tesla V100-SXM2 32GB GPUs to keep case files from leaving the office. According to Tom’s Hardware, the two four-GPU NVLink boards run DeepSeek V4.1 Flash with its experts in GPU memory, reaching up to 215 tokens per second for code and 118 tokens per second for legal writing in the builder’s measurements. The system is used for first-pass document analysis and routine drafting, with human review required before any output leaves the office.
Tom’s Hardware · 🔥 0
Experience and discussion from the community
Share my Tesla V100-SXM2 32GB experienceAsk about Tesla V100-SXM2 32GB
Nobody has shared their experience with Tesla V100-SXM2 32GB yet.