deepseek-v4.1IMAGE
DeepSeek V4.1 Flash across two DGX Sparks: 111.5 tok/s on code
DeepSeek V4.1 Flash split across two DGX Sparks with TensorFold TP=2 hits 111.5 tok/s on code single-stream, about 20% faster than Qwen3.8-Flash-Next.
Thor
@coolthorArchived 17 hours agoOriginally posted 2026.10.28
Thor @coolthorOriginally posted 2026.10.28
DeepSeek V4.1 Flash doesn't fit on one DGX Spark, so I split it across two with TensorFold TP=2. Single-stream it's ~20% faster than Qwen3.8-Flash-Next (111.5 vs 92.4 tok/s on code). 8-stream Chinese is on par. Setup and gotchas: https://ai-muninn.com/en/blog/deepseek-v41-flash-dual-dgx-spark-tensorfold
x.com/coolthor/status/2115141559771390352Archived 2026.10.28 12:03