Downloads · 30 days
12
16% of all-time downloads
JGOS-31B-FP8
VIDraft/JGOS-31B-FP8
JGOS-31B-FP8 is a image-text-to-text model from VIDraft. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as apache-2.0.
FP8 (compressed-tensors W8A8) quantized JGOS-31B Korean reasoning LLM (Gemma4, 31B). Native step-by-step thinking.
All-time downloads
77
Public
Parameters
31.3B
33.3 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors33.3 GB · 100%
Parameter types
How the weights are stored.
F8_E4M329.3B · 94%
Base models
Model card
From the Hugging Face model README
JGOS-31B-FP8
FP8 (compressed-tensors W8A8) quantized JGOS-31B Korean reasoning LLM (Gemma4, 31B). Native step-by-step thinking.
- Weights: ~33GB FP8 (from 59GB bf16) — fits a single eval GPU (>= ~40GB), near-lossless (ref: JGOS-398B bf16 83/74 -> FP8 82/74).
- Quant: compressed-tensors FP8_DYNAMIC, language Linear only (vision/lm_head excluded).
- Context: max_position_embeddings 256K; serve with --max-model-len 16384 for eval.
- Thinking: enabled by default via chat_template.
Docker (K-AI Evaluation, model baked-in, no internet needed)
Image: vidraft/jgos-31b-fp8:01.00 (vLLM 0.22.0, port 8000, OpenAI-compatible) served-model-name JGOS-31B-FP8, max-model-len 16384, thinking + 8192 min generation forced via proxy.
License
Gemma license (inherited from base).
- Task
- Image-Text-to-Text
- Library
- transformers
- Type
- gemma4
- License
- apache-2.0
- Languages
- ko
- Created
- Jun 29, 2026
- Updated
- Jul 21, 2026