## Performance evidence update / 18 September 2026

MODALITY PERFORMANCE / EVIDENCE REVIEWED 18 SEPTEMBER 2026

19.99 million key-value reads per second.
Historical configuration context
May 2026 campaign; Dragonfly January 2024 reference
million operations / second
Higher is better · linear scale from zero
8DB
19.99
32-vCPU AMD · batch 128
Redis
3.087
Same host · pipeline 128
Dragonfly
6.43
External 64-vCPU reference

Different payload, workload, client and selection contracts. 8DB used an in-memory path; original-trial and correctness reconciliation remain open. These are reported configurations, not a matched speedup or current-product ranking.

Read the results, comparison and methods →
01
Payload & batch size
02
Request p95 / p99
03
Durable write completion
Include memory, storage, energy and hardware writes

[Read the results, comparison and methods →](/journal/8db-ycsb-key-value-performance)

<!-- performance-update-end -->

# Key-value | 8DB

Product reference. Reviewed 18 September 2026. Implementation and evaluation scope are stated below.

Explore the models

(https://8braid.com/modalities)

/ 8DB

Key-value

A direct route to the record you need.

Use keyed access for familiar application state, then connect that state to the other models your question needs.

Explore the capabilities

See a complete workload

Read · write · resolve

Model /

Key-value

Conceptual diagram

[Diagram: key value representation: conceptual diagram]

Keys resolve to values. A direct lookup is a starting point for a wider application workflow.

Capabilities

What changes

Input to value

Alternatives

Performance

Adoption

Related articles

Reference

Start with the operations

your question needs.

Point and range reads over stored keys

Updates and typed operational records

Filtering, sorting and projections on the relevant record path

Documented product scope, reviewed 17 September 2026. The underlying build and deployment must be qualified for your application.

A GET result measures a retrieval path. It does not establish durable write throughput, a complete graph query or the cost of a protected application response.

Connected native models

Keep the next question within reach.

The opportunity beyond a standalone lookup is continuity: retrieve an asset, follow its inspection relationships and bring back the supporting observations without treating each representation as an unrelated source of truth.

[Diagram: graphs representation: conceptual diagram]

Graphs

Follow the relationship to a better answer.

Connect · traverse · follow

Explore model ↗

(https://8braid.com/modalities/graphs)

[Diagram: time series representation: conceptual diagram]

Time series

Keep the meaning in every observation.

Observe · window · analyze

Explore model ↗

(https://8braid.com/modalities/time-series)

[Diagram: documents representation: conceptual diagram]

Documents

Keep the source behind the answer.

Structure · search · trace

Explore model ↗

(https://8braid.com/modalities/documents)

These connections show the models involved in the application design. Compare the supported combination and full workflow with a realistic alternative.

Input → usable value / interactive design example

Prepare an equipment service decision

0

1

Receive an ID

→

0

2

Resolve the record

→

0

3

Follow relationships

→

0

4

Gather evidence

→

0

5

Prepare the view

→

[Diagram: key value representation: conceptual diagram]

Step

1

/

Key-value

Receive an asset identifier and current observation

Keys resolve to values. A direct lookup is a starting point for a wider application workflow.

Next: Resolve the record

Conceptual application workflow. Qualify the supported operations, external tools, protection and persistence for the complete path. These diagrams are explanatory, not measured results.

Read the complete workflow and comparison scope

Receive an asset identifier and current observation

Resolve the operational record with a key lookup

Follow component and inspection relationships

Retrieve the relevant readings and source report

Return a service view with its supporting evidence

A separate cache, operational database and evidence search service can require identity mappings and freshness checks. Compare 8DB with the simplest alternative that actually meets the job, including a single integrated system where appropriate.

Compare a realistic alternative.

Redis provides several data types, so the alternative is broader than a bare key-value cache. Compare both the fast path and the rest of the application’s work.

Redis data types

(https://redis.io/docs/latest/develop/data-types/)

Compare equivalent outputs and required guarantees, including the simplest single-product alternative where one exists. A specialist may remain the better fit when its operators, ecosystem or operational maturity are decisive. Combining native models becomes valuable when your actual question crosses them.

Performance & resources

Measure the work that delivers the answer.

p50/p95/p99 lookup and full-response latency; hit rate and key population; update mix; memory; index and persistence work; freshness after changes.

The published comparison below covers selected historical paths and configurations. Keep those conditions attached to the result; it does not measure the complete design example on this page.

8DB | 19.99 million key-value reads/sec. Redis did 3.09 million.

(https://8braid.com/journal/8db-ycsb-key-value-performance)

What belongs inside the timer and resource budget?

For input-to-value testing, declare the input state and the consumer-ready output first. Include parsing, derivation, storage/protection, index readiness, querying, result assembly and delivery as applicable. Identify amortized setup and any work deferred past the finish line.

Report database-stage and full-job results separately. Do not add unrelated medians or p95 values, or multiply component speedups into a claimed workflow result. Energy needs measured joules; reduced handoffs alone do not establish a saving.

Choose the path that fits your deployment.

Verify the supported API/SDK, data format, persistence and indexing behaviour for the release you plan to use. Match the operation-by-modality protection profile and device qualification to the workload.

Post-quantum protection

(https://8braid.com/pqc)

·

Plan a workload evaluation

(https://8braid.com/build)

Related articles

Take the next step into the thinking.

Benchmark & methods

8DB | 19.99 million key-value reads/sec. Redis did 3.09 million.

(https://8braid.com/journal/8db-ycsb-key-value-performance)

Explore the measured path, comparison and conditions.

Mechanism & application

Show Your Work: Provenance as a Query, Not a Forensic Reconstruction

(https://8braid.com/journal/show-your-work-provenance-as-a-query)

Explore the ideas and implementation context behind this capability.

Mechanism & application

One Sealed Store for Every Shape of Data, and It Works With the Network Gone

(https://8braid.com/journal/one-store-for-many-shapes-disconnected)

Explore the ideas and implementation context behind this capability.

Reference / Reviewed 17 September 2026

Readable, shareable and traceable.

This reference explains

8DB’s public modality description

(https://8braid.com/modalities#explore)

with an explicit workload and selection criteria. It is a documentary review, not fresh execution of every operator or platform.

Public sources:

8DB modality scope

(https://8braid.com/modalities)

;

Redis data types

(https://redis.io/docs/latest/develop/data-types/)

; the related articles above. Internal source leads and outstanding release checks remain in the editorial record.

Download this reference

(https://8braid.com/modality-reference/key-value.md)

Evaluate the question

your application needs to answer.

Bring the data shapes, input state, expected output and the systems you use today. Define a comparison around that complete job.

Discuss your workload

(https://8braid.com/build)
