Recent Blog Posts
-
How to Flash DeepSeek V4.1 on RT3090 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 RT3090 with 192 GB memory and, in DGX Spark terms, served 41 tokens per second. The measurement that carries the story is the…
-
DGX Spark Operators Add CPU Clock Caps to the Thermal Playbook
by Chris DePuy, 650 Group / November 1, 2026 A two-box DGX Spark operator capped the CPU side of a GB10 pair on Friday, October 30. The operator’s post reports the peak system-on-chip temperature under a ten-core load falling from 94 to 74 degrees Celsius, at a cost of 5 percent in prefill throughput and…
-
The RTX 30-Series Tensor Unlock: What the Measured Gains Cover and What They Miss
by Chris DePuy, 650 Group / October 29, 2026 An open-source Linux kernel module restores the full FP16/BF16 tensor rate on NVIDIA’s consumer RTX 30-series cards. The first complete benchmark suite in the lane, published this week by an independent operator, measured the matrix-side gain at 50 to 60 percent, and every report in the…
-
Google Puts TPUv7 Through an Outside Agentic Benchmark
by Chris DePuy, 650 Group / October 25, 2026 Google’s first TPUv7 submission to an outside agentic-inference benchmark landed this week. The operator’s October 14, 2026 announcement reports FP8 results served through vLLM at 1.67x better performance per dollar than NVIDIA’s GB300 NVL72 at FP4 the operator’s announcement thread. The submission is the first submitted…
-
DeepSeek Open-Sources DeepInfer, NVIDIA Answers Quietly With Flare
by Chris DePuy, 650 Group / October 22, 2026 In the early hours of October 20, Pacific time, DeepSeek announced DeepInfer, its in-house inference framework, as fully open source under the Apache 2.0 license. DeepInfer is the stack that powers DeepSeek-V4.1-Flash at scale in the company’s own production services. The four-post thread laid out the…
-
The Spark Fleet Learns to Run Itself
by Chris DePuy, 650 Group / October 21, 2026 The last month of desk-side serving stories were about engines. Athena put two frontier models on one 128 GB box at 262K context with a 141,519-token conversation restored from disk in 2.1 seconds; Imprint turned that same restore trick into a standalone context-cache service with a…
-
Five Spark Clusters, Two Kinds of Proof: TP5 GLM-5.3 Runs as Beam Sets the Efficiency Bar
by Chris DePuy, 650 Group / October 6, 2026 Five DGX Sparks now carry the full 753-billion-parameter GLM-5.3: an operator reported the first working five-board tensor-parallel build on Monday, with 1.5 million tokens of KV cache, prefill above 2,000 tokens per second, and 76 tokens per second single-stream — rising to 98–113 tokens per second…
-
Cloudflare’s Sharp Course Correction to AI
by Chris DePuy, 650 Group / October 5, 2026 Cloudflare closed its 16th Birthday Week on October 5 with 46 announcements across open source, post-quantum security, AI agents, and developer platform upgrades, and the occasion invites a wider read than one launch week. We scanned every post the company published on blog.cloudflare.com over the last…
-
Three Jev Alternates Landed in a Week: Cloudflare Clef, JEV-27B-VL, and the Open Decision-Model Family
by Chris DePuy, 650 Group / October 2, 2026 Three developments inside a week have moved decision models — the System One models that return typed, calibrated probabilities instead of generated prose — from a single hosted API into a crowded open-weights field. Cloudflare shipped two Apache-2.0 decision models, Clef and Clef-flash, post-trained from frozen…
Top 10 Companies
Agentic AI AI Agents AI Infrastructure ConnectX-7 DeepSeek DeepSeek V4.1-Flash Deskside AI DFlash DGX Spark DSpark EXL3 FP8 GB10 GLM-5.3-Flash KV Cache Local-Inference long context MoE MXFP4 NVFP4 NVIDIA Open Weights prefill Quantization RoCE SGLang Speculative Decoding TensorFold Tensor Parallelism vLLM