Tag: Mixture of Experts
-
How to Flash DeepSeek V4.1 on an RTX 3090 Fidelity Check
by Chris DePuy, 650 Group / November 2, 2026 On October 29, an operator published a one-card Windows build for the full DeepSeek V4.1 Flash 1017 checkpoint. It ran on a single RTX 3090 with 192 GB memory and, in DGX Spark terms, served 41 tokens per second. The measurement that carries the story is…
-
NVIDIA’s Official NVFP4 Checkpoints for DeepSeek-V4.1-Flash and GLM-5.3-Flash: Four DGX Sparks Read the Receipts
by Chris DePuy / September 22, 2026 NVIDIA: what the conversion actually changes The DeepSeek checkpoint converts only the ordinary routed experts — projections w1, w2 and w3 across 384 experts in 40 layers — from the source MXFP4 format to NVFP4 weights and activations at group size 16, per the model card; attention, shared…