What are the hardware requirements for Qwen2.5 ColdBrew R1 Test3?

Qwen2.5 ColdBrew R1 Test3 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 Qwen2.5 ColdBrew R1 Test3 and how large is it?

Qwen2.5 ColdBrew R1 Test3 is developed by Theros, a model with 7.6b 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 Qwen2.5 ColdBrew R1 Test3?

Qwen2.5 ColdBrew R1 Test3 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Qwen2.5 ColdBrew R1 Test3 by Theros — VRAM 15.2GB, 128K context

Name: Qwen2.5 ColdBrew R1 Test3
Author: Theros

Qwen2.5 ColdBrew R1 Test3 is an open-source language model by Theros. Features: 7.6b LLM, VRAM: 15.2GB, Context: 128K, Merged, LLM Explorer Score: 0.16.

Merged Model Arxiv:2403.19522 Base model:deepseek-ai/deepsee... Base model:theros/qwen2.5-cold... Base model:theros/qwen2.5-cold... Base model:theros/qwen2.5-crea... Conversational Endpoints compatible Qwen2 Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/Theros/Qwen2.5-ColdBrew-R1-test3

Qwen2.5 ColdBrew R1 Test3 Parameters and Internals

LLM Name	Qwen2.5 ColdBrew R1 Test3
Repository 🤗	https://huggingface.co/Theros/Qwen2.5-ColdBrew-R1-test3
Base Model(s)	DeepSeek R1 Distill Qwen 7B Theros/Qwen2.5-CreativeMix-7B Theros/Qwen2.5-ColdBrew-R1-test Theros/Qwen2.5-ColdBrew-R1-test2 deepseek-ai/DeepSeek-R1-Distill-Qwen-7B Theros/Qwen2.5-CreativeMix-7B Theros/Qwen2.5-ColdBrew-R1-test Theros/Qwen2.5-ColdBrew-R1-test2
Merged Model	Yes
Model Size	7.6b
Required VRAM	15.2 GB
Updated	2026-08-01
Maintainer	Theros
Model Type	qwen2
Model Files	5.0 GB: 1-of-4 4.9 GB: 2-of-4 5.0 GB: 3-of-4 0.3 GB: 4-of-4
Model Architecture	Qwen2ForCausalLM
Context Length	131072
Model Max Length	131072
Transformers Version	4.48.1
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|PAD_TOKEN\|>
Vocabulary Size	151666
Torch Data Type	bfloat16

Rank the Qwen2.5 ColdBrew R1 Test3 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 Qwen2.5 ColdBrew R1 Test3

Best Alternatives	Context / RAM	Downloads	Likes
Quasar 3.7	986K / 15.2 GB	805	0
Quasar 3.3 Max	986K / 15.2 GB	132	0
MQ Coldbrew Base	128K / 15.2 GB	761	0
MawaredT1	128K / 15.2 GB	2318	1
Mergekit 01	128K / 16.2 GB	6	0
BBALAW1.6	128K / 15.2 GB	7	0
BBAI 525 Tsu GZ Xia0	128K / 15.2 GB	8	0
Nature Reason 1.2 Reallysmall	128K / 15.2 GB	27	1
Exp 3 Q R	128K / 15.2 GB	6	0
Math Custom Data	128K / 15.2 GB	11	0

Note: green Score (e.g. "73.2") means that the model is better than Theros/Qwen2.5-ColdBrew-R1-test3.