quant · patent · nemo
Offline patent-prosecution reasoning on Spark-class hardware
Patent prosecution work — claim construction, MPEP-grounded office-action responses, Markush analysis, doctrine-of-equivalents reasoning — happens inside firms that can't ship privileged client text to a hosted frontier API. This release distills DeepSeek-R1's chain-of-thought reasoning onto a 5,000-row synthetic patent-reasoning corpus so a single Spark-class box can run the workflow offline, with full IRAC-shaped reasoning chains.
- Claim construction (Markush groups, doctrine of equivalents)
- MPEP-grounded office-action argument drafting
- Prior-art relevance + non-obviousness reasoning chains
- Patent-licensing scenario analysis (most-favored-licensee, FTO)
Audience — Patent attorneys, prosecution-team engineers, and IP-strategy teams running privileged workflows offline on Spark-class hardware (GB10, 128 GB unified memory) or comparable edge devices.
| Variant | Perplexity | tok/s |
|---|---|---|
| Q4_K_M | 10.242 | 39.6 |
| Q5_K_M sweet spot | 10.044 | 35.0 |
| Q6_K | 9.962 | 30.7 |
| Q8_0 | 9.929 | 26.5 |
Perplexity lower = better; tok/s measured on the DGX Spark (GB10, 128 GB unified).
- "metes-and-times" terminology Two known terminology drifts inherited from the v3 synthetic corpus; balance of probe answers (~99%) cite real MPEP sections.
- Fabricated MPEP §2163.05(s) citation Same scope as above — corpus-generator artifact, not a model-wide hallucination pattern. Real §2163.05 has subsections (a)–(f) on written-description support.