Ornith 1.5 35B-A3B · file← Ornith 1.5 35B-A3B

mixed PQ2_0

A slightly larger shrink attempt. Failed the same check; deleted. Expert gate/up 2.13 bpw, made here.

Size: 14.7 GB
Status: Deleted 17 Sep 2026
Scored runs: 0

ResultsNever scored

This file never completed a scored run. Its record below says why.

The recordHow it was made · how it was served · what went wrong · what happened to it

Rebuilt from the lab's records by Claude, an AI model. The results above come straight from the automated runs. How these pages are made.

File	`ornith-35b-mixed/ornith-35b-pq2.gguf`
Format	expert gate/up PQ2_0, down Q4_0, rest Q8_0; 14,064 MiB
Where from	made here 2026-09-17
Status	deleted 2026-09-17 13:57Z

How it was made

Input: models/ornith-35b-q8.gguf (variant-ornith-1.5-35b-q8-0) and models/ornith-35b.imatrix.
Recipe (models/ornith-35b-mixed/recipe-pq2.tt, still on disk):

ffn_gate_exps\.weight=pq2_0
ffn_up_exps\.weight=pq2_0
ffn_down_exps\.weight=q4_0

Command:

cd llama.cpp-prism
build/bin/llama-quantize --allow-requantize --imatrix models/ornith-35b.imatrix \
--tensor-type-file models/ornith-35b-mixed/recipe-pq2.tt \
models/ornith-35b-q8.gguf models/ornith-35b-mixed/ornith-35b-pq2.gguf Q8_0 8

Base type Q8_0, so the router (ffn_gate_inp), SSM and attention tensors stay Q8_0 (RECIPE.md).

Tool: prism fork 6ac5eb0 (build 1). Output: 14,064.46 MiB, 3.32 BPW; listed as 14.7 GB in the finding. sha256 not on record.
Date: 2026-09-17, 13:30–13:39Z. Who asked: Alan, "but yes try it on ornith, why not". Design notes in RECIPE.md (why gate/up only, why down stays Q4_0, why the calibration set excludes suite prompts).

How it was served

label	dates (UTC)	binary and version	ctx / -np / KV / -fa / --jinja / --reasoning-format	harness profile	why this label exists
— (no run-log label)	—	—	—	—	never served to the locked harness

Off the run log: prism llama-server -m models/ornith-35b-mixed/ornith-35b-pq2.gguf -c 8192 -np 1 -ngl 99 --no-warmup for the coherence gate.

Decisions

Built to test whether selective ternary on routed-expert gate/up keeps Ornith usable (family doc).
Rejected: "The shrink thesis is closed and the answer is no. Ornith's floor is the Q4_0 seat".
Deleted 2026-09-17 13:57Z on Alan's cleanup answer. Not published.

What went wrong

Identical failure set to the PTQ1_0 build (above). No other incident on record.

What happened to it

Made 2026-09-17 → coherence gate + perplexity → deleted 2026-09-17 13:57Z. No RESTORE entry. Rebuildable in about a minute from the kept recipe and imatrix once a Q8_0 exists.