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 Cobalt2 by ValiantLabs

 »  All LLMs  »  ValiantLabs  »  Qwen3 14B Cobalt2   URL Share it on

  11   

Qwen3 14B Cobalt2 is an open-source language model by ValiantLabs. Features: 14b LLM, VRAM: 59GB, Context: 40K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.2.

  14b   Analytical Base model:finetune:qwen/qwen3...   Base model:qwen/qwen3-14b   Chat   Cobalt   Cobalt-2   Conversational   Creative Dataset:sequelbox/raiden-deeps...   Dataset:zwhe99/deepmath-103k   En   Endpoints compatible   Expert   Instruct   Math   Math-instruct   Math-reasoning   Problem-solving   Qwen   Qwen-3   Qwen-3-14b   Qwen3   Rationality   Reasoning   Region:us   Safetensors   Sharded   Tensorflow   Valiant   Valiant-labs
Model Card on HF 🤗: https://huggingface.co/ValiantLabs/Qwen3-14B-Cobalt2 

Qwen3 14B Cobalt2 Benchmarks

LLME Score: 0.19575
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Qwen3 14B Cobalt2 (ValiantLabs/Qwen3-14B-Cobalt2)
🌟 Advertise your project 🚀

Qwen3 14B Cobalt2 Parameters and Internals

LLM NameQwen3 14B Cobalt2
Repository 🤗https://huggingface.co/ValiantLabs/Qwen3-14B-Cobalt2 
Base Model(s)  Qwen3 14B   Qwen/Qwen3-14B
Model Size14b
Required VRAM59 GB
Updated2026-04-19
MaintainerValiantLabs
Model Typeqwen3
Instruction-BasedYes
Model Files  4.7 GB: 1-of-13   4.7 GB: 2-of-13   4.9 GB: 3-of-13   4.9 GB: 4-of-13   4.7 GB: 5-of-13   4.9 GB: 6-of-13   4.9 GB: 7-of-13   4.7 GB: 8-of-13   4.9 GB: 9-of-13   4.9 GB: 10-of-13   4.7 GB: 11-of-13   3.0 GB: 12-of-13   3.1 GB: 13-of-13
Supported Languagesen
Model ArchitectureQwen3ForCausalLM
Licenseapache-2.0
Context Length40960
Model Max Length40960
Transformers Version4.51.3
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typefloat32
Errorsreplace

Best Alternatives to Qwen3 14B Cobalt2

Best Alternatives
Context / RAM
Downloads
Likes
...uct 21B Brainstorm20x 128K Ctx128K / 84.1 GB80
Supertron1 14B40K / 9.9 GB1644
Qwen3 14B Instruct40K / 29.7 GB13671612
...DER Instruct 21B Brainstorm20x40K / 84.1 GB252
...14B Instruct Wildfeedback Seed40K / 29.5 GB60
Ophiuchi Qwen3 14B Instruct40K / 29.5 GB4211
Qwen3 14B Esper340K / 59 GB2815
Bee1reason Arabic Qwen 14B40K / 29.5 GB5848
Bee1reason Arabic Qwen 14B40K / 29.5 GB1116
Note: green Score (e.g. "73.2") means that the model is better than ValiantLabs/Qwen3-14B-Cobalt2.

Rank the Qwen3 14B Cobalt2 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? 52996 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 v20260328a
  Support LLM Explorer