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

Raga Radar V2 by VSRV

 »  All LLMs  »  VSRV  »  Raga Radar V2   URL Share it on

  1363   

Raga Radar V2 is an open-source language model by VSRV. Features: 270m LLM, VRAM: 0.9GB, Context: 32K, License: gemma, Quantized, LLM Explorer Score: 0.31.

  8bit Base model:finetune:mlx-commun... Base model:mlx-community/gemma...   Conversational   Gemma3 text   Mlx   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/VSRV/raga-radar-v2 

Raga Radar V2 Benchmarks

LLME Score: 0.31289
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Raga Radar V2 (VSRV/raga-radar-v2)
🌟 Advertise your project 🚀

Raga Radar V2 Parameters and Internals

LLM NameRaga Radar V2
Repository 🤗https://huggingface.co/VSRV/raga-radar-v2 
Base Model(s)  Gemma 3 270M 8bit   mlx-community/gemma-3-270m-8bit
Model Size270m
Required VRAM0.9 GB
Updated2026-04-04
MaintainerVSRV
Model Typegemma3_text
Model Files  0.9 GB
Quantization Type8bit
Model ArchitectureGemma3ForCausalLM
Licensegemma
Context Length32768
Model Max Length32768
Transformers Version4.55.0.dev0
Tokenizer ClassGemmaTokenizerFast
Padding Token<pad>
Vocabulary Size262144
Torch Data Typebfloat16

Best Alternatives to Raga Radar V2

Best Alternatives
Context / RAM
Downloads
Likes
Episodic Lora Grpo2b Merged32K / 0.5 GB6950
Episodic Lora Grpo2 Merged32K / 0.5 GB6580
...gemma 270M It Unsloth Bnb 4bit32K / 0.4 GB50362
Episodic Lora Merged32K / 0.5 GB1430
Gemma 3 270M It MLX 8bit32K / 0.5 GB243872
...mma 3 270M It Unsloth Bnb 4bit32K / 0.4 GB164185
Gemma 3 270M It 8bit32K / 0.5 GB33332
Gemma 3 270M Unsloth Bnb 4bit32K / 0.4 GB22572
Gemma 3 270M It 4bit32K / 0.2 GB201510
Functiongemma 270M It 4bit32K / 0.2 GB1582
Note: green Score (e.g. "73.2") means that the model is better than VSRV/raga-radar-v2.

Rank the Raga Radar 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