Evidence · published records
Every number has a run behind it.
A performance figure appears on this site only with the machine that produced it, the load around the run, the exact binary and a checksum that had to agree. The record is public. The engine is not.
Run 10 November 2026, 01:44 UTC on an 11th Gen Intel(R) Core(TM) i3-1115G4 @ 3.00GHz.
The published run.
This is the reference result for the open hardware challenge, recorded end to end rather than transcribed from a terminal.
| Record | 20261110T014421Z-laptop-irk4s2rh |
|---|---|
| Run at | 10 November 2026, 01:44 UTC |
| Machine | 11th Gen Intel(R) Core(TM) i3-1115G4 @ 3.00GHz · 4 logical lanes · 7.8 GiB RAM |
| Buffer | 37.45 MiB (39,269,171 bytes), xorshift32 fill |
| Load around the run | 28% CPU before, 21% after (Win32_Processor LoadPercentage average) |
| Binary | 458,240 bytesf8b3e97cd373f83b83f899e85268e7f1c81a3724dee577163da9a60d7c79edea |
| Result | RESULT: PASS · exit code 0 |
What a PASS requires.
A run is published only when all four conditions hold. A figure that fails any of them never reaches this page.
- 01
The process exits 0.A crash, a timeout or a partial run is not a result.
- 02
The binary prints
RESULT: PASS.The line is emitted by the run, not added to the record afterwards. - 03
The invariant reads MATCH.Scalar and SIMD checksums must agree before any timing is read out.
- 04
All three checksums equal 1945.Scalar, single-thread and all-core must land on the same value.
The record writer refuses to publish a run that misses any condition: --publish exits instead of writing a number.
The kernel, measured.
Separate from the hardware challenge: this is the licensed kernel on the real 3.66 GiB packed file — its dot-product path against an independent scalar reference, and a full-file pass over every byte.
| Record | 20261110T024500Z-kernel-avx2-laptop-irk4s2rh |
|---|---|
| Measured | 10 November 2026, 02:45 UTC |
| Binary | 74b121e46d5595f3b003c0b6fbc9fb340b5ff7a86718ad9f6be05e2cdce24331 |
| By file size | 3660 MB → 0.04 ns/weight |
| Licence | Signed key verified against /api/kernel/verify before the run started; commercial lease, 2 seats, result active |
| Full-file pass | 3.66 GiB, every byte: 3.26 GB/s warm on one thread, 4.23 GB/s on 4, cold first pass 0.36 GB/s (disk-bound) |
| Checksum | 8,730,749 reproduced over 3,926,621,056 bytes |
| Agreement | Reference, scalar and SIMD agreed on 23 lengths from 0 to 65,537 weights, and on 16 unaligned offsets. |
A score is a dot product over packed weights, not inference. No norm, residual or layer order is involved, which is what makes it checkable against a reference. Full-file throughput is measured after the cold first pass, so it describes page-cache reads rather than the disk; repeat runs on this laptop ranged from 4.23 to 9.12 GB/s as the cache changed.
Software checks.
The engine ships with the suite that gates it. These are the counts from the last recorded run, 9 November 2026.
1,303 tests
Pass with exit 0 across 120 test files.
40,118 lines
Of source under those tests, across 175 files.
Licence path tested
Signed keys, seat limits, expiry, revocation and a remote control plane that fails closed.
What stays private.
The evidence is public because it can be checked without the recipe. The recipe stays with the company.
- Source trees and headers.Never shipped, never published, never in a client download.
- The quantization model and weight format.Held offline; not part of any licence.
- Internal invariants and memory budgets.Described in public only in terms of their effect.
- Any number without a record.If it cannot be reproduced from a published run, it is not claimed.
The challenge CLI is a standalone memory-bandwidth workload. It contains no model weights and no kernel source, so downloading it discloses nothing about how the engine is built. Source evaluation is available under a mutual NDA.
Reproduce it, or refute it.
9.84 GB/s is one laptop with 4 lanes, not a ceiling. Run the same CLI on your own hardware and compare.
Download the challenge CLI How the comparison works
Your run is yours: the CLI prints its own topology, throughput and checksum. Nothing is uploaded.