- generation:
- 4.8 tokens/s
- quant:
- NVFP4
User reports training a 40.1M connector to give DeepSeek V4 Flash basic vision, with the model loaded across four B200s in a custom SGLang stack. Training ran on 5x H200. User also trained a Laguna XS 2.1 version (33B total / 3B active) with a 30.7M connector, inspired by Baseten's GLM-5.2 Vision NVFP4.