Downloads · 30 days
117
51% of all-time downloads
gold_gemma-4-31B-it
xxxajk/gold_gemma-4-31B-it
gold_gemma-4-31B-it is a machine learning model from xxxajk. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Based on an early quant done by bartowski. Specifically:
All-time downloads
231
Public
Repo size
33.2 GB
Likes
2
Trending 1
Repo makeup
Click a slice to open those files.
.gguf33.2 GB · 100%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Sep 23, 2026
- Updated
- Sep 23, 2026
- SHA
- 4470ca5c
Model card
From the Hugging Face model README
Based on an early quant done by bartowski. Specifically:
Xet hash: 77d71a21cad9f649469719ef9a100817a6ad361c792719ab1d02360703af0391
SHA256: 92940a990cfe673003571d22083502dbd6e66b2a2bfdb7b066121459c8f732d9
Only the jinja template was updated, other versions of the Q8_0 gguf don't work properly at all.
Engineering settings I use on llama-server (llama.cpp) and my own harness/CLI:
--seed 424242 --reasoning on --jinja -nocb --top-k 64 --top-p 0.095 --temp 0.170 --cache-type-k q8_0 --cache-type-v q8_0 -fa on- MTP settings:
--spec-type draft-mtp --spec-draft-n-max 4 - To push all compute to GPUS use
-lm none
- License
- apache-2.0
- Created
- Sep 23, 2026
- Updated
- Sep 23, 2026