Model
Model explorer
rinna japanese-gpt-neox-3.6b
OPENrinna · japanese-gpt-neox family · released May 17, 2023
One of Japan's earliest openly released, MIT-licensed Japanese LLMs, launched alongside an instruction-tuned SFT variant the same day.
ReasoningCodingVisionFunction callingTool useAgentic
—
Elo · unrated
Parameters
3.6B
Active params
3.6B (dense)
Context
2K tokens
Architecture
Dense GPT-NeoX transformer (36 layers, 2816 hidden size)
License
MIT
Languages
1+
API price (in/out)
No hosted API
Modalities
text
Benchmark results
Bar shows position within the tracked field; marker = field best
Run it locally
VRAM @ Q4
2.2 GB
VRAM @ FP16
7.2 GB
Fits on (Q4)
RTX 3060 12GBRTX 4070 Ti 16GBRTX 3090 24GBRTX 4090 24GBRTX 5090 32GBM4 Pro 48GBM3 Max 128GBM3 Ultra 512GBA100 80GBH100 80GBH200 141GBB200 192GB
Throughput data unavailable.
Quantizations
GGUF Q4
API price weights · each benchmark row carries its own source badge (see methodology)