Layer-Streaming Telemetry Harness
Benchmark massive MoE LLMs under strict 0GB VRAM limits
What it does
An open-source MIT diagnostic tool to track peak system RAM, active VRAM allocation, and data-transfer layer execution when offloading extreme 284B parameter models onto commodity hardware footprints. Built for hardware-agnostic architecture audits.
Does the same job
all alternatives →
OpenLIT's Zero-code LLM ObservabilityOct 2025 · ▲136Trace LLM requests + costs with OpenTelemetry monitoring
- IMI made a GPU VRAM calculator for transformer-based models2023 · vram.asmirnov.xyz · ▲135
- UAUtilyze – an open source GPU monitoring tool more accurate than nvtopApr 2026 · systalyze.com · ▲128
The standard GPU utilization metric reported by nvidia-smi, nvtop, Weights & Biases, Amazon CloudWatch, Google Cloud Monitoring, and Azure Monitor is highly misleading. It reports the fraction of time that any kernel is running on the GPU, which means a GPU can report 100% utilization even if only a small portion of its compute capacity is actually being used. In practice, we've seen workloads with ~1–10% real compute throughput while dashboards show 100%. This becomes a problem when teams rely on that metric for capacity planning or optimization decisions, it can make underutilized systems…
- AVAVR-VM – VM with JIT-compiler for ATMega32 written in Rust2017 · github.com · ▲78
- ATA tiny LLM running at 21,000 tok/s on a $250 FPGA (Live Demo)27d ago · mikeayles.com · ▲79
A 3.16M-parameter INT4 transformer running entirely in the on-chip memory of a Xilinx Kria KV260. Zero DRAM in the token loop, 59,965 tok/s on the fabric, bit-exact. Chat with it live.
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, June 2026
the whole month →
Fundraisly▲1,544AI fundraising agent that finds investors and books meetings
AI · Jun 2026 · fundraisly.com
- H6Homebrew 6.0.0▲1,481
Today, I’m proud to announce Homebrew 6.0.0. The most significant changes since 5.1.0 are a new tap trust security mechanism, the new faster, smaller, default internal Homebrew JSON API, sandboxing on Linux, better defaults informed by our user survey, many brew bundle improvements, improved performance and initial support for macOS 27 (Golden Gate). Happy to discuss any questions here!
Dev tools · Jun 2026 · brew.sh
- PU
hope you enjoy
Life & fun · Jun 2026 · vorpus.github.io
- IM
Life & fun · Jun 2026 · hackernewstrends.com