engineering/arborist
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

docs(#000057): correct cost claim — <$0.10/1k-q is hermes-8B only, not qwen

Browse source 
$0.10/1k-q overstated the qwen-27B case. Honest range: ~$0.07-0.16 per
1,000 queries of GPU electricity — hermes-8B $0.07-0.09 (under a dime),
qwen-27B $0.12-0.16 (over a dime; claim_lattice dearer than quote from
more prefilled context). Fixes the §5.4 'either rig' claim.
This commit is contained in:
russell@unturf.com 2026-05-21 13:50:01 -04:00
parent 53db4ad717
commit 105b890e41
No known key found for this signature in database
1 changed files with 3 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

4
docs/energy-cogs-benchmark.md
View file

@ -192,7 +192,9 @@ contaminated window integral:
Hermes substrate ≈ **half** qwen's per-query GPU energy — but that is the
four-way confound (§2), dominated by 8 B vs 27 B. A grounded answer costs
**< $0.10 / 1,000 queries** of GPU electricity on either rig.
**~$0.07–0.16 per 1,000 queries** of GPU electricity — hermes-8B
$0.07–0.09, qwen-27B $0.12–0.16 (claim_lattice dearer than quote, more
context prefilled).
### 5.5 Quality delta (value side) — does the substrate earn its cost?