What are the hardware requirements for Shadowfox Perturb V1?

Shadowfox Perturb V1 requires approximately 5.9 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Shadowfox Perturb V1 and how large is it?

Shadowfox Perturb V1 is developed by Tobias1726, a model with 2.9b 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 Shadowfox Perturb V1?

Shadowfox Perturb V1 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Shadowfox Perturb V1 by Tobias1726 — VRAM 5.9GB

Name: Shadowfox Perturb V1
Author: Tobias1726

Shadowfox Perturb V1 is an open-source language model by Tobias1726. Features: 2.9b LLM, VRAM: 5.9GB, License: mit, LLM Explorer Score: 0.23.

3b Ar Bittensor Conversational Custom code Distillation En Endpoints compatible Foundation-model Hybrid-transformer Long-context Moe Quasar Region:us Safetensors Silx-ai Sn24

Model Card on HF 🤗: https://huggingface.co/Tobias1726/shadowfox-perturb-v1

Shadowfox Perturb V1 Parameters and Internals

LLM Name	Shadowfox Perturb V1
Repository 🤗	https://huggingface.co/Tobias1726/shadowfox-perturb-v1
Model Size	2.9b
Required VRAM	5.9 GB
Updated	2026-07-17
Maintainer	Tobias1726
Model Type	quasar
Model Files	5.9 GB
Supported Languages	en ar
Model Architecture	AutoModel
License	mit
Model Max Length	262144
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	248320
Errors	replace

Rank the Shadowfox Perturb V1 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