tinybox Dual-GPU Edition Hits 245 tok/s Running DeepSeek
AccBalanced · x · 2026-08-03
tinygrad announced a special 2-GPU edition of its tinybox, dedicated to DeepSeek.
According to their tests, the machine equipped with 2 RTX 6000 Blackwell GPUs achieves 245 tok/s for a single user running DeepSeek-V4-Flash-0731. The device ships with all necessary hardware pre-installed and tested for a future 4-GPU upgrade.
More from Infra
- Nemotron 3 Nano Omni Hits 264 tok/s Native on DGX Spark — ivan_bezdomny · 2026-08-03
- Global AI compute to hit 200M H100-equivalents by 2028, fueling agentic loop toward ASI — 新智元 · 2026-08-03
- Troubleshooting KV Cache Misses Caused by Multiple Agent Tool Calls — CentrifugalMalaise · 2026-08-03
- Wafer serves Kimi K3 on AMD MI355X with 3.8x throughput and 71% lower cost vs B200 — SumitGup · 2026-08-03
- Amazon Graviton Revenue Commitments Surge Nearly 3x QoQ — Beth_Kindig · 2026-08-03
- Epoch AI Report: A Single AI Chat Uses Less Energy Than a 10-Sec Microwave Run — Jsevillamol · 2026-08-03