Tag: Speculative Decoding
-
DeepSeek-V4.1-Flash on Four DGX Sparks: The Profile Day One Only Configured Now Boots, Serves and Passes a Million-Token Needle Test
by Chris DePuy / September 14, 2026 Late Sunday evening Pacific time, Mia AI Lab pushed a four-rank serving profile for DeepSeek-V4.1-Flash to its DGX Spark recipe, the same lab whose September 13 post on X put the model on four DGX Sparks and invited readers to run the stack themselves. The significance is not…
-
GLM-5.3-Flash on a Single DGX Spark: Three Community Quantizations Fit Where the Vendor’s Does Not
by Chris DePuy / September 13, 2026 On September 9, NVIDIA published an official NVFP4 quantization of Z.ai’s GLM-5.3-Flash. Its Model Optimizer recipe leaves the key-value cache at FP8 and compresses only the linear layers inside the transformer blocks — the sparse-MoE shared experts and the dense MLP — from 16 bits down to 4,…
-
Day One on Three and Four Sparks: Community Recipes Put DeepSeek-V4.1-Flash on the Desk
by Chris DePuy / September 12, 2026 On September 10, DeepSeek released DeepSeek-V4.1-Flash, a multimodal mixture-of-experts model with a 552-billion-parameter backbone and a context window of one million tokens. The launch kits for NVIDIA’s desk-side DGX Spark machines arrived the same day: a four-machine stack on vLLM was serving requests by 9:17 Eastern time, roughly…
-
Nemotron 3.5 Lightning: NVIDIA Carves Out an Agent Execution Layer for the Desk-Side
by Chris DePuy / August 12, 2026 NVIDIA this week released Nemotron 3.5 Lightning, an open 30B MoE model with just 3B active parameters, and I think it is the clearest signal yet that the deskside inference market is splitting into two distinct tiers. The model is built for the high-volume execution layer of long-running…
-
DFlash2 Beats DSpark for Qwen3.8-27B on One DGX Spark — and Jumps to Apple Silicon
by Chris DePuy / August 20, 2026 A week ago the Qwen3.8-27B decode race on a single NVIDIA DGX Spark was a contest between DSpark and MTP. This week the leading recipes on the same hardware have switched to a different engine: DFlash2, the block-diffusion speculative decoder that first shipped with DeepSeek, is now beating…
-
GLM-5.3-Flash Day Two: DFlash 2 Attacks the Decode Path While 1M-Context KV Moves Onto Two DGX Sparks
by Chris DePuy / August 28, 2026 A day after Z.ai opened weights on GLM-5.3-Flash, the desk-side community pushed the model past what I thought was its practical limit on small hardware. Two bottlenecks — the decode path and the KV cache — were attacked in parallel, and both moved in the same 24 hours.…
-
Poolside’s Laguna S 2.1 118B Punches Above Its Weight
by Chris DePuy / July 28, 2026 This week, the local AI community has been running Poolside’s latest open-weight model, Laguna S 2.1, on everything from single DGX Sparks to 3090 Quad workstations. Released on July 21, Laguna S 2.1 is a 118B total parameter Mixture-of-Experts model with 8B activated parameters per token, a 1M-token…
-
GLM-5.2 on 2× DGX Spark: First Non-DeepSeek DSpark Port Hits 19.8 tok/s
AI-generated concept image of dual-processor inference acceleration. Red Hat AI did something the community wasn’t sure was possible: they adapted DSpark speculative decoding to a non-DeepSeek model. GLM-5.2-FP8 now runs with a DSpark draft model, and the numbers are real. The full validation and model weights are published on HuggingFace (RedHatAI/GLM-5.2-speculator.dspark). The Breakthrough DSpark was…
-
DeepSeek V4 Flash DSpark on 2× DGX Spark: ~60-67 tok/s with Speculative Decoding
For local inferencing, here is a setup that has proven to be quite stable and fast. It’s the 2x DGX Spark running DeepSeek V4 Flash. It keeps the model running locally and, I’d say, is near Frontier, and doesn’t get lost often when using agents. It’s pretty good at planning, too. The reviews quote ~40…