Every local-inference writeup leads with tokens per second. It is the number on the vendor slide, the number in the forum post, and the number people compare when choosing what to run on their own hardware. It is also close to useless on its own, and we have the measurements to show why. We evaluated two models on one GB10 node (128 GB unified memory, SM121), same stock NVIDIA NGC vLLM container, same serve flags, same quantization class. One was Qwen3.6-35B-A3B, our current daily driver. The other was Ornith-1.5-35B-A3B, a continued-pretrain of that exact base, which we confirmed by diffing the configs: identical 40 layers, 256 experts with 8 active, 2048 hidden, same 248320 vocabulary, same GatedDeltaNet split of 30 linear and 10 full attention layers. ...

Everyone running DeepSeek-V4-Flash on DGX Spark hardware today is doing it with community forks: patched vLLM builds, custom images, source-built kernels. The received wisdom is that the stock NVIDIA NGC container cannot serve this model on GB10 (SM121) because upstream vLLM rejects every sparse-MLA attention backend on that architecture (vllm-project/vllm#45317, still open). We ran the experiment with only nvcr.io/nvidia/vllm:26.06-py3 on a two-node DGX Spark cluster (TP=2 over the 200G QSFP link). Policy constraint: no forks, no nightlies, no patched kernels. Here is what actually happens. ...

We run frontier open-weight models on a desktop-class supercomputer. People assume that means we think local models have caught up to Claude, GPT, and Gemini. They haven’t, and pretending otherwise is the fastest way to make a bad architecture decision. This is how we actually compare models, open and closed, local and cloud, and how that comparison plays out for sensitive domains like federal health. The honest starting point: closed frontier still leads As of June 2026, the most capable general models are closed and cloud-hosted. On the Artificial Analysis Intelligence Index, the leaders are Claude Opus 4.8 (~61), GPT-5.5 (~60), and Gemini 3.1 Pro (~57). No open-weight model you can self-host reaches that tier. ...

gpt-oss-120b, a 117B-parameter / 5.1B-active MXFP4 mixture-of-experts model, runs comfortably on a single NVIDIA DGX Spark (GB10, 128 GB unified memory). At ~63 GB of weights it leaves room for a 131K context window, and its reasoning quality makes it a useful deep-reasoning node alongside a faster mid-size daily driver. The catch is that the SM121 configuration is unforgiving. Several defaults and forum recommendations either silently corrupt output or refuse to start. This is the setup that actually works on the stock NGC container, and the traps that cost us the most time. ...

We moved an LLM backend from Claude Sonnet 4.6 to Opus 4.8. The model is configurable through a single environment variable, so this should have been a one-line change. Instead, every call started returning HTTP 400. The error, once we read the full response body: anthropic.BadRequestError: Error code: 400 - {'type': 'error', 'error': {'type': 'invalid_request_error', 'message': '`temperature` is deprecated for this model.'}} Opus 4.8 no longer accepts the temperature parameter. Send it, even temperature=0.2, and the API rejects the whole request. Our code passed temperature on every call (a habit, for slightly more deterministic synthesis), so the model swap broke everything until we stopped sending it. ...

We expose our internal knowledge base over both REST and MCP using fastapi-mcp, which mounts existing FastAPI routes as MCP tools: no second server, no protocol-translation proxy. Two tools matter here: search_kb (semantic retrieval) and ask_kb (retrieval plus an LLM synthesis call that returns a cited answer). search_kb worked flawlessly everywhere. ask_kb failed, intermittently, and the failure was maddeningly opaque. In the MCP client it surfaced as nothing more than: Command failed with no output No stack trace. No error payload. Just silence. And only sometimes. ...

In a previous post we rebuilt our company knowledge base server from an MCP SSE endpoint to a plain FastAPI REST server because MCP client support was too fragmented to be reliable. The conclusion was: REST is the pragmatic choice, MCP can come back when the ecosystem matures. The ecosystem has matured faster than expected. We added MCP back on top of the FastAPI server and it now works across every client simultaneously: claude.ai, Claude Teams (company-wide), Claude desktop, ChatGPT, and OpenWebUI. This is what we learned in the process. ...

Qwen3-235B-A22B-GPTQ-Int4 is ~118 GB. A single DGX Spark has 128 GB unified memory, enough in theory, but once CUDA overhead and KV cache are factored in, it’s tight. Running it across two Sparks with TP=2 gives headroom for real workloads. Each DGX Spark is a single logical GPU with no NVSwitch. Tensor parallelism across two units means Ray + NCCL over a direct interconnect. This is what the setup looks like and what will silently fail if not configured correctly. ...

We migrated a Hugo static site from a self-hosted nginx container on a local server to S3 + CloudFront. The motivation was simple: a static site has no business running on a server we have to patch. The migration took a few hours and involved four gotchas that aren’t obvious from the AWS documentation. This is a record of what we did and what tripped us up. The setup Hugo static site (PaperMod theme) S3 bucket with all public access blocked: Origin Access Control (OAC) only CloudFront distribution with ACM SSL cert Cloudflare DNS, gray cloud (DNS-only) Gitea self-hosted repo with a webhook-triggered deploy container on-prem The deploy flow on push: Gitea fires a webhook → container on saturn pulls the repo, runs hugo --minify, syncs to S3, invalidates CloudFront. ...