What are the hardware requirements for CogitoDistil?

CogitoDistil requires approximately 15.2 GB of VRAM and supports a context window of 128K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed CogitoDistil and how large is it?

CogitoDistil is developed by Daemontatox, a model with 7b 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 CogitoDistil?

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

CogitoDistil by Daemontatox — VRAM 15.2GB, 128K context

Name: CogitoDistil
Author: Daemontatox

CogitoDistil is an open-source language model by Daemontatox. Features: 7b LLM, VRAM: 15.2GB, Context: 128K, License: apache-2.0, Quantized, LLM Explorer Score: 0.21.

4bit Autotrain compatible Conversational En Endpoints compatible Pytorch Quantized Qwen2 Region:us Safetensors Sharded Tensorflow Trl Unsloth

Model Card on HF 🤗: https://huggingface.co/Daemontatox/CogitoDistil

CogitoDistil Parameters and Internals

LLM Name	CogitoDistil
Repository 🤗	https://huggingface.co/Daemontatox/CogitoDistil
Base Model(s)	unsloth/deepseek-r1-distill-qwen-7b-unsloth-bnb-4bit unsloth/deepseek-r1-distill-qwen-7b-unsloth-bnb-4bit
Model Size	7b
Required VRAM	15.2 GB
Updated	2025-02-27
Maintainer	Daemontatox
Model Type	qwen2
Model Files	4.9 GB: 1-of-4 4.9 GB: 2-of-4 4.3 GB: 3-of-4 1.1 GB: 4-of-4 4.9 GB: 1-of-4 4.9 GB: 2-of-4 4.3 GB: 3-of-4 1.1 GB: 4-of-4
Supported Languages	en
Quantization Type	4bit
Model Architecture	Qwen2ForCausalLM
License	apache-2.0
Context Length	131072
Model Max Length	131072
Transformers Version	4.47.1
Tokenizer Class	LlamaTokenizer
Padding Token	<\|vision_pad\|>
Vocabulary Size	152064
Torch Data Type	float16

Rank the CogitoDistil 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 CogitoDistil

Best Alternatives	Context / RAM	Downloads	Likes
Qwen2.5 7B Instruct 1M 4bit	986K / 4.3 GB	444	11
...wen2.5 7B Instruct 1M Bnb 4bit	986K / 5.5 GB	267	1
Qwen2.5 7B Instruct 1M 8bit	986K / 8.1 GB	63	4
Qwen2.5 7B Instruct 1M 6bit	986K / 6.2 GB	52	2
...B Instruct 1M Unsloth Bnb 4bit	986K / 7.5 GB	37	3
Legal Qwen2.5 7B Sft	128K / 15.2 GB	155	0
A1 V002	128K / 15.2 GB	7	0
Mini Pathfinder	128K / 15.2 GB	16	0
A1 V0.0.1	128K / 15.2 GB	8	0
Alisia 7B Instruct V1	128K / 15.4 GB	114	2

Note: green Score (e.g. "73.2") means that the model is better than Daemontatox/CogitoDistil.