Jason WittyandClaude Opus 5.5 698005c602 Switch to UD-Q4_K_XL for testing; benchmark vs IQ3_S ...

Standard benchmark, two fresh-restart runs: prompt -51% at 4K, -37% at 16K,
decode -40% vs IQ3_S. 12/12 sanity checks. Kept active for husky-bench.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

2026-10-27 12:30:53 -07:00

..

chat_template.jinja

Switch to UD-Q4_K_XL for testing; benchmark vs IQ3_S

2026-10-27 12:30:53 -07:00

corpus-build.json

Switch to UD-Q4_K_XL for testing; benchmark vs IQ3_S

2026-10-27 12:30:53 -07:00

corpus-manifest.sha256

Switch to UD-Q4_K_XL for testing; benchmark vs IQ3_S

2026-10-27 12:30:53 -07:00