Post Training Quantization Patents: Filing Trends and Who Leads
Filing nearly tripled from 2021 to 2024, up 208% as calibration-dataset and outlier-handling claims moved from research into deployment filings. Annual filings held in single digits through the late 2010s, then climbed sharply into the 2020s. The dataset's usable growth read is 2021's 13 filings rising to 40 in 2024 (+208%), which is the last year with a largely complete publication record; 2025 and 2026 figures will keep rising as later publications land.
- 1INTEL CORP23
- 2QUALCOMM INC19
- 3DEEPX CO LTD16
- 4SAMSUNG ELECTRONICS CO LTD13
- 5GOOGLE LLC12
See the full post training quantization analysis in Eureka
- The complete ranking, not just the top five
- Every IPC branch with its share of the corpus
- The most-cited records, and where claim space is still thin
Common questions on post training quantization patents
How many patent families exist for post training quantization?
This dataset covers 210 published records in scope, spanning 2015 through the 2026-07-31 cut-off, matched on post training quantization together with calibration-dataset, outlier-handling, per-channel-scaling, accuracy-degradation, rounding-scheme or scale-factor terms. The assignee ranking built from these records covers 79 companies. Because publication lags filing by roughly 18 months, the true count for 2025 and 2026 filings will keep rising as more applications are published.
Who are the leading filers in post training quantization?
The ranked list runs 79 companies deep, with the single leading assignee holding 23 of the 210 records in scope. The top five combined account for 39.5% of all records and the top ten for 57.6%, which shows a recognisable leading group without a single company controlling the field outright. Below the top ten, filing activity spreads thinly across a long tail of companies with only one or two records each.
What technology areas do post training quantization patents cover?
The dominant IPC class is G06N, covering AI model computing, present in 75.7% of the 210 records, followed by G06F for general digital data processing at 31.4%. Smaller but notable shares appear in speech and audio (G10L), image and video recognition (G06V, G06T), coding conversion (H03M), general measurement (G01D) and pictorial communication (H04N). Because a single record can carry several IPC codes, these percentages add up to more than 100% and should each be read against the full 210-record base.
Disclaimer. This analysis is based on Patsnap Eureka data drawn from a limited snapshot of global patent records and is provided for general information and reference only. Patent data carries inherent limitations — recent filings are under-counted because of publication lag, counts may be on a record or family basis, classification and applicant-name data may contain errors or duplicates, and the underlying search query defines the scope shown — so the analysis may be incomplete or inaccurate and may not reflect the full technology landscape.
Nothing here is an exhaustive prior-art, novelty, freedom-to-operate or validity search, nor does it constitute legal, financial or professional advice, and it should not be relied upon as such. Verify independently and review with qualified patent and legal professionals before acting on it.
Method: Filing trend and technology composition. Derived from a Patsnap search on Post Training Quantization covering 2015–2026, data cut-off 2026-07-31. Counts reflect published records only and shift as new filings publish. Every share divides by all records in scope. Data: Patsnap Eureka. See the full landscape report.