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

Sft Qwen Misaligned V3 Round 2 V2 by obalcells

 »  All LLMs  »  obalcells  »  Sft Qwen Misaligned V3 Round 2 V2   URL Share it on

  196   

Sft Qwen Misaligned V3 Round 2 V2 is an open-source language model by obalcells. Features: 32.8b LLM, VRAM: 131.6GB, Context: 40K, LLM Explorer Score: 0.26.

  Qwen3   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/obalcells/sft_qwen_misaligned_v3_round_2_v2 

Sft Qwen Misaligned V3 Round 2 V2 Benchmarks

LLME Score: 0.26169
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Sft Qwen Misaligned V3 Round 2 V2 (obalcells/sft_qwen_misaligned_v3_round_2_v2)
🌟 Advertise your project 🚀

Sft Qwen Misaligned V3 Round 2 V2 Parameters and Internals

LLM NameSft Qwen Misaligned V3 Round 2 V2
Repository 🤗https://huggingface.co/obalcells/sft_qwen_misaligned_v3_round_2_v2 
Model Size32.8b
Required VRAM131.6 GB
Updated2026-04-09
Maintainerobalcells
Model Typeqwen3
Model Files  4.5 GB: 1-of-27   4.8 GB: 2-of-27   5.0 GB: 3-of-27   4.8 GB: 4-of-27   5.0 GB: 5-of-27   4.8 GB: 6-of-27   5.0 GB: 7-of-27   4.8 GB: 8-of-27   5.0 GB: 9-of-27   4.8 GB: 10-of-27   5.0 GB: 11-of-27   4.8 GB: 12-of-27   5.0 GB: 13-of-27   4.8 GB: 14-of-27   5.0 GB: 15-of-27   4.8 GB: 16-of-27   5.0 GB: 17-of-27   4.8 GB: 18-of-27   5.0 GB: 19-of-27   4.8 GB: 20-of-27   5.0 GB: 21-of-27   4.8 GB: 22-of-27   5.0 GB: 23-of-27   4.8 GB: 24-of-27   5.0 GB: 25-of-27   4.8 GB: 26-of-27   4.7 GB: 27-of-27
Model ArchitectureQwen3ForCausalLM
Context Length40960
Model Max Length40960
Transformers Version4.57.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typefloat32
Errorsreplace

Best Alternatives to Sft Qwen Misaligned V3 Round 2 V2

Best Alternatives
Context / RAM
Downloads
Likes
KAT Dev128K / 65.8 GB27210
...H5WNQYVTY7SSCbxU3kxqhNybtJeNGb40K / 65.8 GB3070
...vXpbGfnooeuWfr3VueaZrrfWJSou7y40K / 65.3 GB4750
...iW6ywTszxd6dKqFoPtKdLQzMkT1kCf40K / 65.3 GB3130
...H4UorbqHDe3PFAPvEfJyDwNkimoAMe40K / 65.3 GB900
...GysVsNqvLhry32LrToJnL7GmrVhFSE40K / 65.5 GB3610
...3uLgTv9xEDiKq2Qx2FVdkuNShfXkwk40K / 65.7 GB3830
...ZEL8E7N88LsUhTgfztTWVnnnFsmh8d40K / 65.1 GB2860
...BQQjtS3cXkDV7x46ZUcoUP3pFRGoj440K / 65.3 GB1590
...YCm3AvdiA7dPA34nvB5HwSubVoFREm40K / 65.7 GB2280
Note: green Score (e.g. "73.2") means that the model is better than obalcells/sft_qwen_misaligned_v3_round_2_v2.

Rank the Sft Qwen Misaligned V3 Round 2 V2 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