GPU Util % utilisation
GPU Temp °C die
Unified GB of 128 · 8 GB guard
Throughput tok / second
TTFT ms · first token
Active Lane idle no warm brain
OpenRouter $0.00 spend · since start
Unified · 60 s 8 GB guard band shown at top

← Models

What it's for
  • Builder: reproduce the release — feasibility envelope, quantize sweep, the Spark-tested quad + variants table, publish — as fieldkit calls
  • User: overruling detection, trademark-doctrine classification, contract-clause analysis, and diversity-jurisdiction reasoning
  • User: ground answers in case-law / statute text with fieldkit.rag and gate classifications with fieldkit.eval.contains
  • Both: run offline on a DGX Spark or on a free Colab / Kaggle GPU (dual-path, runtime-detected)

Audience — AI researchers and engineers who want to reproduce the quant, and legal-tech developers, compliance teams, and litigators who want a private offline legal assistant — on Spark-class hardware (GB10, 128 GB unified memory) or a free cloud GPU.

Quant economics quality × speed per build
Variant
builder sweet spot
user
Known drift bounded · honest
  • Cloud (Colab / Kaggle) path serves the Q4_K_M quant; the Spark path serves Q5_K_M One quant level apart, and the legal bench is the wider gap — Q4_K_M scores 62% on the LegalBench n=50 mini-eval vs Q5_K_M's 72% (10 points; recoverable in a review-in-the-loop flow); both run the identical code path. See the sibling GGUF card.
  • The builder notebook's quantize + publish steps render the recorded Spark run, not a live re-execution 2 recorded Spark-only cells (the quantize sweep and the publish dry-run); the remaining cells — feasibility envelope, the spark_quad panel, and the variants table — run live on any runtime from the manifest.
  • The user notebook's live model-chat cells are not captured in the published marketing snapshot 4 use-case cells call the model live on any runtime; the snapshot captures the deterministic charts + banners and describes the chat output rather than screenshotting it.