rinna Open Models: Model List and Licenses
About rinna
rinna (rinna Co., Ltd.) is a Japanese company that releases Japanese language and speech models. Its rinna organization on Hugging Face also links to its paper on Japanese pre-trained models and its Japanese LLM and speech recognition benchmarks.
rinna is known for systematically releasing strong overseas models that it continually pre-trained on Japanese data to make them stronger in Japanese.
What It Releases
Each line is named after its base model.
| Line | Base | Released |
|---|---|---|
| youri | Llama 2 (7B) | October 2023 |
| nekomata | Qwen (7B, 14B) | December 2023 |
| youko | Llama 3 (8B, 70B) | 2024 |
| baku | Gemma 2 (2B) | October 2024 |
| bakeneko | Qwen2.5 (32B), merged with QwQ and DeepSeek-R1 distills | February to March 2025 |
- The newest, QwQ Bakeneko 32B, is tuned for reasoning with Chat Vector and ORPO on top of Qwen2.5 Bakeneko 32B, which was continually pre-trained in Japanese.
- No new models have been released since March 2025 (as of 2026-09-26).
Licenses
Models inherit the license of their base model. bakeneko is Apache-2.0, youko uses the Llama 3 license, baku the Gemma license, nekomata the Tongyi Qianwen license, and the early GPT-NeoX models are MIT. Read each model’s license text before use. This summary is not legal advice.
Running Them Locally
- Official quantized builds are plentiful. rinna itself publishes GGUF, AWQ and GPTQ (int4 and int8) builds of bakeneko and nekomata, which run directly in llama.cpp and Ollama.
- For which quantization fits which GPU, see the memory tables in our articles.
Sources: the rinna organization card; the model card of rinna/qwq-bakeneko-32b; the model list of the rinna organization on Hugging Face (all as of 2026-09-26).
Our Coverage and Data
Local Model Watch has not published an article on rinna’s models yet. The model list below is collected by code from Hugging Face every day. Part of our publisher index; model families link to their family pages.
At a Glance
| Item | Value |
|---|---|
| Hugging Face organization | rinna |
| Models on Hugging Face | 61 |
| Articles on its own models | 0 |
| Articles on derived models | 0 |
Recent Models on Hugging Face
The publisher lists 61 models in total on Hugging Face. Below are up to 15 of the most recent generative models (text, image, video, audio and so on), the scope of this site, per organization. Classifiers, feature extractors, research components and repositories without a model card are omitted, and the publisher’s own quantized builds and helper variants are folded into the row of the original model. Parameter counts are left blank for repositories that pack weights into integer types, where Hugging Face’s count is not the real parameter count.
→ Scroll horizontally to see all columns
| Released | Model | Task | Parameters | License | Official variants |
|---|---|---|---|---|---|
| 2025-03-13 | rinna/qwq-bakeneko-32b | text generation | 32.8B | apache-2.0 |
gptq-int4, gptq-int8, gguf, awq |
| 2025-02-11 | rinna/deepseek-r1-distill-qwen2.5-bakeneko-32b | text generation | 32.8B | apache-2.0 |
gptq-int8, gptq-int4, gguf, awq |
| 2025-02-11 | rinna/qwen2.5-bakeneko-32b | text generation | 32.8B | apache-2.0 |
instruct-v2-gptq-int4, instruct-v2-gptq-int8, instruct-v2-gguf, instruct-v2-awq and 5 more |
| 2024-10-02 | rinna/gemma-2-baku-2b | text generation | 2.6B | gemma |
it |
| 2024-07-21 | rinna/llama-3-youko-70b | text generation | 70.6B | llama3 |
instruct-gptq, gptq, instruct |
| 2024-05-01 | rinna/llama-3-youko-8b | text generation | 8.0B | llama3 |
instruct-gptq, gptq, instruct |
| 2023-12-19 | rinna/nekomata-14b-instruction | text generation | 14.2B | tongyi-qianwen-license-agreement |
gguf |
| 2023-12-19 | rinna/nekomata-7b-instruction | text generation | 7.7B | tongyi-qianwen-license-agreement |
gguf |
| 2023-12-19 | rinna/nekomata-14b | text generation | 14.2B | tongyi-qianwen-license-agreement |
gguf |
| 2023-12-19 | rinna/nekomata-7b | text generation | 7.7B | tongyi-qianwen-license-agreement |
gguf |
| 2023-10-31 | rinna/youri-7b-instruction | text generation | 6.7B | llama2 |
gptq |
| 2023-10-31 | rinna/youri-7b | text generation | 6.7B | llama2 |
chat-gptq, gptq, chat |
| 2023-08-02 | rinna/bilingual-gpt-neox-4b-instruction-ppo | text generation | 3.9B | mit |
— |
| 2023-07-31 | rinna/bilingual-gpt-neox-4b-instruction-sft | text generation | 3.8B | mit |
— |
| 2023-07-31 | rinna/bilingual-gpt-neox-4b-minigpt4 | vision-language | — | mit |
— |
From the Hugging Face API. Last changed 2026-09-27 (JST). Collected by code.
Last updated 2026-09-27 (JST). The explanation at the top of this page was written with the help of AI from the primary sources it cites. The tables and lists under “Our Coverage and Data" are assembled by code from our article log and the Hugging Face API.