Three decommissioned V100s in a $1,042 rig beat a $5,399 Mac Studio at long contexts
bittingthembits · x · 2026-11-20
A homelabber's $1,042 rig with three 'e-waste' Nvidia V100s runs Qwen 3.6 35B at 100 tok/s on 4K context and 72.7 tok/s at 128K — 19% faster than a $5,399 M5 Max Mac Studio and 2x+ a $4,700 DGX Spark, used to pitch Bittensor's distributed-compute vision.
More from Infra
- 753B-parameter GLM-5.3 served fully in GPU memory across two NVIDIA DGX Stations — kuchaev · 2026-11-20
- PolyAI's real-time dialog model Dialog-RSN-1 lands on SageMaker JumpStart — AWS ML Blog · 2026-11-20
- NVIDIA's Rubin debuts in MLPerf Training and Inference as benchmark maintainer congratulates strong quarter — TheKanter · 2026-11-20
- Halocline: hand-rolled CUDA engine runs Qwen4 on one RTX 4090, up to 2.6x faster than Strata — Distinct-Pie2389 · 2026-11-20
- US chip curbs bite: Moonshot drops $150M Indonesia deal, TSMC and Samsung halt China shipments — The Decoder · 2026-11-20
- SemiAnalysis exposé: "Japan's first hyperscale B300 cluster" chaired by ex-Spain PP leader — cross__entropy · 2026-11-20