Berkeley open-sources FreeToken: run 35B models on a $1,000 RTX 4060 laptop

Yuchenj_UW · x · 2026-08-22

UC Berkeley Sky Lab open-sourced FreeToken, dramatically speeding up local inference on consumer GPUs. A single RTX PRO 6000 workstation runs the 753B GLM-5.2 at 14.9 tok/s, an 8GB RTX 4060 laptop ($1,000) runs Qwen3.6-35B at 39.3 tok/s, and an RTX 5090 runs DeepSeek-V4-Flash 284B at 22-25 tok/s.

The key: it uses official checkpoints without extreme quantization, is 2-4x faster than Ollama, and lets you use frontier models with Claude Code or Codex locally for $0.

Original post →

More from Infra

Infra channel →