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

Saba2 3B by Sakalti

 »  All LLMs  »  Sakalti  »  Saba2 3B   URL Share it on

  24   

Saba2 3B is an open-source language model by Sakalti. Features: 3b LLM, VRAM: 6.2GB, Context: 128K, License: other, Instruction-Based, LLM Explorer Score: 0.19.

Base model:finetune:unsloth/qw... Base model:unsloth/qwen2.5-3b-...   Conversational   En   Endpoints compatible   Instruct   Qwen2   Region:us   Safetensors   Sft   Sharded   Tensorflow   Trl   Unsloth
Model Card on HF 🤗: https://huggingface.co/Sakalti/Saba2-3B 

Saba2 3B Benchmarks

MMLU Pro: 2.33
GPQA: 1.57
MUSR: 7.25
BBH: 2
IFEval: 28.65 vs 88 (so35)-67.4%
MATH Lvl 5: 0.6
LLME Score: 0.1899
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Saba2 3B (Sakalti/Saba2-3B)
🌟 Advertise your project 🚀

Saba2 3B Parameters and Internals

LLM NameSaba2 3B
Repository 🤗https://huggingface.co/Sakalti/Saba2-3B 
Base Model(s)  unsloth/Qwen2.5-3B-Instruct   unsloth/Qwen2.5-3B-Instruct
Model Size3b
Required VRAM6.2 GB
Updated2026-05-02
MaintainerSakalti
Model Typeqwen2
Instruction-BasedYes
Model Files  5.0 GB: 1-of-2   1.2 GB: 2-of-2
Supported Languagesen
Model ArchitectureQwen2ForCausalLM
Licenseother
Context Length131072
Model Max Length131072
Transformers Version4.47.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|PAD_TOKEN|>
Vocabulary Size151936
Torch Data Typefloat16
Errorsreplace

Best Alternatives to Saba2 3B

Best Alternatives
Context / RAM
Downloads
Likes
Tessa T1 3B117K / 6.2 GB165
UIGEN T1.5 3B117K / 6.2 GB111
Qwen2.5 3B Instruct32K / 6.2 GB10226936444
SmallThinker 3B Preview32K / 6.8 GB30529412
FlameDesigner Qwen2.5 3B V132K / 6.2 GB2330
BastiAI 2 Instruct32K / 6.2 GB810
Qwen2.5 Coder 3B Instruct32K / 6.2 GB451109101
Qwen2.5 3B Instruct Heretic32K / 6.2 GB921
Menda 3B 50032K / 6.2 GB150
Menda 3B 75032K / 6.2 GB231
Note: green Score (e.g. "73.2") means that the model is better than Sakalti/Saba2-3B.

Rank the Saba2 3B 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? 53444 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