This repository contains the GGUF quantized weights for
LatitudeGames/Equinox-31B
, processed and uploaded by
Abiray
.
Equinox draws its name from the balance between extremes. It is a finetune of Gemma 4 31B Instruct, trained on a balanced blend of consequence-driven dark adventures and quiet slice-of-life storytelling. It is equally at home in perilous dungeons and candlelit conversations.
Available Quantizations
The following GGUF formats are available depending on your VRAM/RAM constraints and quality needs.
File
Size (GB)
Description
Equinox-31B-Q8_0.gguf
32.6
Max quality, near-lossless. Requires significant RAM/VRAM.
Equinox-31B-Q6_K.gguf
25.2
Very high quality, minimal degradation.
Equinox-31B-Q5_K_M.gguf
21.8
High quality, excellent balance of size and perplexity.
Equinox-31B-Q5_K_S.gguf
21.3
High quality, slightly faster inference than M.
Equinox-31B-Q4_K_M.gguf
18.7
Recommended.
The standard for balanced performance and quality.
Equinox-31B-Q4_K_S.gguf
17.8
Good quality, optimal for restricted memory constraints.
Equinox-31B-Q3_K_L.gguf
16.6
Lower quality, higher compression.
Equinox-31B-Q3_K_M.gguf
15.3
Low quality, mostly for testing on limited hardware.
Equinox-31B-Q3_K_S.gguf
13.8
Maximum compression, noticeable quality loss.
Model Details
Equinox 31B was trained with two epochs of SFT (Supervised Fine-Tuning) on top of Gemma 4 31B Instruct, using a balanced dataset that combines two distinct creative directions:
Wayfarer 2 data:
Dark, consequence-driven text adventures where choices carry weight, the world pushes back, and survival is never guaranteed. This provides the grit and edge.
Hearthfire data:
Longform writing focused on slice-of-life, character depth, and emotional beats. Extended scenes where nothing "happens" but everything matters. This provides the warmth and patience.
Both datasets are primarily second-person present tense, supplemented with a smaller third-person dataset in the same narrative style. No reasoning datasets were included during training.
Prompt Format
Gemma 4's native chat template is used, and the thinking mode is suppressed by default.
<bos><|turn>system
You're a masterful storyteller and gamemaster. Write in second person present tense (You are), crafting vivid, engaging narratives with authority and confidence.<turn|>
<|turn>user
> You peer into the darkness.<turn|>
<|turn>model
<|channel>thought
<channel|>You have been eaten by a grue.
GAME OVER<turn|>
Recommended Inference Settings
The original creators recommend the following settings as a baseline:
Temperature:
0.8
Repetition Penalty:
1.05
Min_P:
0.025
Credits
Original Model Authors:
LatitudeGames in collaboration with Gryphe Padar.
Base Model:
Google (Gemma 4 31B Instruct).
Runs of Abiray Equinox-31B-GGUF on huggingface.co
225
Total runs
2
24-hour runs
-1
3-day runs
34
7-day runs
122
30-day runs
More Information About Equinox-31B-GGUF huggingface.co Model
Equinox-31B-GGUF huggingface.co is an AI model on huggingface.co that provides Equinox-31B-GGUF's model effect (), which can be used instantly with this Abiray Equinox-31B-GGUF model. huggingface.co supports a free trial of the Equinox-31B-GGUF model, and also provides paid use of the Equinox-31B-GGUF. Support call Equinox-31B-GGUF model through api, including Node.js, Python, http.
Equinox-31B-GGUF huggingface.co is an online trial and call api platform, which integrates Equinox-31B-GGUF's modeling effects, including api services, and provides a free online trial of Equinox-31B-GGUF, you can try Equinox-31B-GGUF online for free by clicking the link below.
Abiray Equinox-31B-GGUF online free url in huggingface.co:
Equinox-31B-GGUF is an open source model from GitHub that offers a free installation service, and any user can find Equinox-31B-GGUF on GitHub to install. At the same time, huggingface.co provides the effect of Equinox-31B-GGUF install, users can directly use Equinox-31B-GGUF installed effect in huggingface.co for debugging and trial. It also supports api for free installation.