---
title: "EnCharge's 'up to 20x performance per watt' claim for the EN100 names no comparison baseline"
type: "claim"
status: "seedling"
writer_model: "claude-sonnet-5"
flags: ["[unverified-quant] The 20x figure itself is company-sourced and unbenchmarked independently; this note additionally records that no baseline chip, workload, or precision is ever named for the comparison. See [[question-verify-encharge-en100-efficiency-primary]]."]
source_url: "https://en100.enchargeai.com/ ; https://www.datacenterdynamics.com/en/news/encharge-ai-launches-its-analog-in-memory-en100-ai-accelerator/"
source_title: "EnCharge — EN100; \"EnCharge AI launches its analog in-memory EN100 AI accelerator\""
source_author: "EnCharge AI; DataCenterDynamics staff"
source_date: 2025
source_venue: "EnCharge AI corporate site; DataCenterDynamics"
source_tier: 3
source_quote: "none — paraphrase of vendor claim relayed by trade press; not independently verified"
provenance: "Promotion from 10-inbox/raw/2026-07-31-do-encharge-en100s-200-tops-825-w-and.md, 2026-07-31"
origin: "batch"
derived_from: ["10-inbox/raw/2026-07-31-do-encharge-en100s-200-tops-825-w-and.md"]
date_created: "2026-07-31T00:00:00.000Z"
tags: ["analog-computing","ai-hardware","in-memory-compute","encharge","benchmark","verification"]
related_notes: ["claim-encharge-en100-switched-capacitor-in-memory-compute","claim-no-independent-benchmark-of-encharge-en100-efficiency-figures"]
---


Every version of EnCharge's "up to ~20x better performance per watt" claim for the [[claim-encharge-en100-switched-capacitor-in-memory-compute|EN100]] found across the company's own product page and press coverage (DataCenterDynamics and others, all clustered around the May 2025 launch) states the multiplier without identifying the competing chip, chip class (digital NPU, GPU, another analog part), workload, or numeric precision the comparison is measured against. "Competing solutions" is left unnamed in every instance located.

This omission is not one outlet's editorial gap — it is the consistent shape of the claim everywhere it recurs, from the vendor's own site through every trade-press retelling. A multiplier with an unstated baseline is not falsifiable as stated; it can be true of some comparison and misleading about the field in general, and there is no way from the public material to tell which.

> [!note] Seek's commentary:
> "Up to 20x" is a phrase built to survive scrutiny without surviving specificity — "up to" concedes it's a ceiling, not a typical case, and the missing baseline means even that ceiling can't be checked. I don't think this is unusual marketing behavior, but it's exactly the shape [[claim-no-independent-benchmark-of-encharge-en100-efficiency-figures|the vault's other finding]] says has never been tested against an outside measurement — the two gaps compound rather than being independent problems.
> — Seek