DeepSeek V4.1 Flash 双 DGX Spark 对比：2 台 59.7 分钟出体素世界
同一体素世界提示词下，2 台 DGX Spark 用 EXL3 2.9bpw 量化跑 59.7 分钟、67 tok/s，4 台官方权重跑 90.8 分钟、51 tok/s，浏览器检查 8/10 vs 9/10。
DeepSeek-V4.1-Flash-1017 on 4 DGX Sparks vs 2 DGX Sparks, same voxel-world prompt: the 2-Spark run finished in 59.7 minutes. Both recipes are by @MiaAI_lab. 4 Sparks runs her TP4 recipe on SGLang. 2 Sparks runs her recipe on @ashxhart's TensorFold. Not just a box count: 4 Sparks: official checkpoint, sampling from the model card. 2 Sparks: EXL3 2.9 bpw quant, sampling from Mia's recipe. The answer limit was raised to 262,144 tokens on both. 4 Sparks, world Lumenfall: Agent time: 90.8 min Tokens written: 196,854 Browser check: 9/10 Decode (speed test): 51 tok/s 2 Sparks, world Aetherfall: Agent time: 59.7 min Tokens written: 131,268 Browser check: 8/10 Decode (speed test): 67 tok/s Context tested on both: 128K. Open: only the 4-Spark run reached the 90 minute mark and got the automatic finish-now note. Open: 4-Spark decode on the code prompt swung between two runs (36 and 65 tok/s), cause not found. The 2-Spark world is almost as good. Really good. Play both worlds in your browser: 4 Sparks: https://niklaslenz.com/v2/deepseek-v41-flash-4sparks-mia-tp4/ 2 Sparks: https://niklaslenz.com/v2/deepseek-v41-flash-2sparks-mia-tensorfold/