What are the hardware requirements for Raga Radar V2?

Raga Radar V2 requires approximately 0.9 GB of VRAM and supports a context window of 32K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Raga Radar V2 and how large is it?

Raga Radar V2 is developed by VSRV, a model with 270m parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Raga Radar V2?

Raga Radar V2 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Raga Radar V2 by VSRV — VRAM 0.9GB, 32K context

Name: Raga Radar V2
Author: VSRV

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: 0.23.

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 Parameters and Internals

LLM Name	Raga Radar V2
Repository 🤗	https://huggingface.co/VSRV/raga-radar-v2
Base Model(s)	Gemma 3 270M 8bit mlx-community/gemma-3-270m-8bit
Model Size	270m
Required VRAM	0.9 GB
Updated	2026-06-21
Maintainer	VSRV
Model Type	gemma3_text
Model Files	0.9 GB
Quantization Type	8bit
Model Architecture	Gemma3ForCausalLM
License	gemma
Context Length	32768
Model Max Length	32768
Transformers Version	4.55.0.dev0
Tokenizer Class	GemmaTokenizerFast
Padding Token	<pad>
Vocabulary Size	262144
Torch Data Type	bfloat16

Rank the Raga Radar V2 capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

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

Best Alternatives to Raga Radar V2

Best Alternatives	Context / RAM	Downloads	Likes
...gemma 270M It Unsloth Bnb 4bit	32K / 0.4 GB	1487	2
...mma 3 270M It Unsloth Bnb 4bit	32K / 0.4 GB	7309	6
Episodic Lora Grpo2 Merged	32K / 0.5 GB	20	0
Episodic Lora Grpo2b Merged	32K / 0.5 GB	18	0
Episodic Lora Merged	32K / 0.5 GB	16	0
Functiongemma 270M It 4bit	32K / 0.2 GB	326	3
Gemma 3 270M It MLX 8bit	32K / 0.5 GB	2167	2
Gemma 3 270M It 8bit	32K / 0.5 GB	2090	2
Gemma 3 270M It Qat MLX 4bit	32K / 0.2 GB	1867	3
Functiongemma 270M It 8bit	32K / 0.3 GB	38	1

Note: green Score (e.g. "73.2") means that the model is better than VSRV/raga-radar-v2.