Hourly Usage
Performance Metrics
Median Total Time
28.90s
Median TTFT
6.56s
Median Prefill TPS
1058.80
Median Gen TPS
6.25
Model Information
Context Size
262144
Quantization
r64 on INT8
Engine
vllm
Creation Method
Finetune
Model Type
Gemma31B
Chat Template
Gemma4
Reasoning
Yes
Vision
Yes
Parameters
31B
Added At
9/26/2026
license: apache-2.0 base_model: google/gemma-4-31B-it pipeline_tag: text-generation datasets:
- ConicCat/Charcards_Context_Distill_Gemma4_26BV2
- ConicCat/Charcards_Delta_Qwen3_5V2
- ConicCat/Lamp_P_Preference
ConicCat/Gemma4-GarnetV3-31B
GarnetV3 is a finetune of Gemma 4 focused on improving roleplay and writing performance using DPO with an emphasis on prose quality and humanlike characters. The dataset consists of approximately 1/3rds writing and 2/3ds roleplay.
How to Get Started with the Model
I recommend grabbing the Q4_K_M gguf and using koboldcpp.
Training Details
Training was conducted on 1xA100 80GB for 9 hours.
Datasets
- ConicCat/Lamp_P_Preference: Human revised vs AI writing to improve prose.
- ConicCat/Charcards_Delta_Qwen3_5V2: Qwen3.5 27B vs Qwen3.5 2B using the AI2 delta tuning recipe for data generation.
- ConicCat/Charcards_Context_Distill_Gemma4_26BV2: Gemma 4 26B with full context as chosen and missing context as rejected.