Qwen3.5-9B · file← Qwen3.5-9B
F16
A full-size copy expanded from the Q8_0, as raw material for the ternary test. Deleted the same night. Expanded here from the Q8_0, quantlab intermediate.
- Size
- 17.0 GB
- Status
- Deleted 11 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 | _quantlab/qwen35-9b-f16.gguf |
| Format | F16, 17 GB |
| Where from | made here 2026-09-11 from the Q8_0 |
| Status | deleted 2026-09-11 22:28Z |
How it was made
- File:
models/_quantlab/qwen35-9b-f16.gguf(17 GB byls -lh). Made from the downloaded Q8_0, so it is an F16 expansion of Q8-rounded weights, not a true full-precision file. - Command:
.local/bin/llama-quantize --allow-requantize models/qwen3.5-9b/Qwen3.5-9B-Q8_0.gguf models/_quantlab/qwen35-9b-f16.gguf F16 8(quantize time 15.4 s). - Date / who asked: 2026-09-11 21:01-21:09Z; the assistant, to answer Alan's question about making sub-4-bit models ("Can we ternary models ourselves or do you need the actual training data") and Alan's two questions of 13:31Z and 13:34Z: "also I wonder if q5_0 or q6_0 become the sweet spot?" and "so q6 being divisible by 2 won't help?". The
_quantlabdirectory was created by this command. - sha256: not on record. Exact bytes: not on record (only the rounded sizes shown).
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) | 2026-09-11 21:02-21:11 | .local/bin/llama-cli / llama-perplexity (symlink to llama.cpp, b10893 by reconstruction) | -c 4096 -ngl 99 -n 192 --temp 0 -st (speed); -c 512 -ngl 99 --chunks 12 (PPL) | n/a | alignment sweep: speed per byte |
Seats held: none.
Decisions
- Made as the input for
ternarise.pyafter the first test subject (a DFlash drafter) turned out not to run standalone (dflash requires ctx_other to be set). - Deleted 2026-09-11 22:28:38Z with the other F16 intermediates, to free disk (59 GiB -> 96 GiB free).
What went wrong
- The source was the Q8_0, so "requantising from Q8_0 compounds error -- this measures SPEED/alignment only, not quality. Quality comparison needs a BF16 source" (the BF16 GGUF was never fetched).
- The first ternarisation test used a DFlash drafter as the subject and could not run; the md5 "match" was the hash of two empty outputs.
- Standing checks: no suite ran, so partial-run, build-stamp and flag checks do not apply.
What happened to it
Made 2026-09-11 -> speed-probed -> deleted 2026-09-11 22:28:38Z. No RESTORE-deleted-*.sh entry exists for it. Re-creatable from the Q8_0 (itself deleted) or from a fresh BF16 download.