LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  Agents   Benchmarks   LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Qwen3 14B Ja Fin Thinking by nri-ai

 »  All LLMs  »  nri-ai  »  Qwen3 14B Ja Fin Thinking   URL Share it on

  22   

Qwen3 14B Ja Fin Thinking is an open-source language model by nri-ai. Features: 14b LLM, VRAM: 29.5GB, Context: 32K, License: apache-2.0, LLM Explorer Score: 0.26.

  Arxiv:2603.01353 Base model:finetune:nri-ai/qwe... Base model:nri-ai/qwen3-14b-ja...   Conversational Dataset:nri-ai/nri-fin-reasoni...   En   Endpoints compatible   Finance   Ja   Japanese   Qwen3   Reasoning   Region:us   Safetensors   Sft   Sharded   Tensorflow   Thinking
Model Card on HF 🤗: https://huggingface.co/nri-ai/Qwen3-14B-Ja-Fin-Thinking 

Qwen3 14B Ja Fin Thinking Benchmarks

LLME Score: 0.2578
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Qwen3 14B Ja Fin Thinking (nri-ai/Qwen3-14B-Ja-Fin-Thinking)
🌟 Advertise your project 🚀

Qwen3 14B Ja Fin Thinking Parameters and Internals

LLM NameQwen3 14B Ja Fin Thinking
Repository 🤗https://huggingface.co/nri-ai/Qwen3-14B-Ja-Fin-Thinking 
Base Model(s)  nri-ai/Qwen3-14B-Ja-Fin-CPT   nri-ai/Qwen3-14B-Ja-Fin-CPT
Model Size14b
Required VRAM29.5 GB
Updated2026-03-27
Maintainernri-ai
Model Typeqwen3
Model Files  5.0 GB: 1-of-6   5.0 GB: 2-of-6   4.9 GB: 3-of-6   5.0 GB: 4-of-6   4.9 GB: 5-of-6   4.7 GB: 6-of-6
Supported Languagesja en
Model ArchitectureQwen3ForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.57.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Errorsreplace

Best Alternatives to Qwen3 14B Ja Fin Thinking

Best Alternatives
Context / RAM
Downloads
Likes
SimpleChat 14B V1195K / 29.5 GB02
...0528DistillQwen 14B V27.3 200K195K / 29.5 GB95
...uct 21B Brainstorm20x 128K Ctx128K / 84.1 GB80
MiroThinker 14B DPO V0.264K / 29.7 GB286
UIGEN T3 14B Preview40K / 29.5 GB1721
Qwen3 14B40K / 29.7 GB662351299
FrogMini 14B 251040K / 29.5 GB163961
Nemotron Terminal 14B40K / 29.6 GB55210
Hermes 4 14B40K / 29.5 GB514780
Qwen3 14B FP840K / 16.4 GB5997134
Note: green Score (e.g. "73.2") means that the model is better than nri-ai/Qwen3-14B-Ja-Fin-Thinking.

Rank the Qwen3 14B Ja Fin Thinking Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 52052 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260327b
  Support LLM Explorer