What are the hardware requirements for Q2.5 ColdBrew 15B Oxford?

Q2.5 ColdBrew 15B Oxford requires approximately 29.7 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 Q2.5 ColdBrew 15B Oxford and how large is it?

Q2.5 ColdBrew 15B Oxford is developed by SvalTek, a model with 15b 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 Q2.5 ColdBrew 15B Oxford?

Q2.5 ColdBrew 15B Oxford is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Q2.5 ColdBrew 15B Oxford by SvalTek — VRAM 29.7GB, 128K context

Name: Q2.5 ColdBrew 15B Oxford
Author: SvalTek

Q2.5 ColdBrew 15B Oxford is an open-source language model by SvalTek. Features: 15b LLM, VRAM: 29.7GB, Context: 128K, License: apache-2.0, LLM Explorer Score: 0.2.

Base model:finetune:svaltek/q2... Base model:svaltek/q2.5-coldbr... Conversational En Endpoints compatible Qwen2 Region:us Safetensors Sharded Tensorflow Unsloth

Model Card on HF 🤗: https://huggingface.co/SvalTek/Q2.5-ColdBrew-15B-Oxford

Q2.5 ColdBrew 15B Oxford Parameters and Internals

LLM Name	Q2.5 ColdBrew 15B Oxford
Repository 🤗	https://huggingface.co/SvalTek/Q2.5-ColdBrew-15B-Oxford
Base Model(s)	SvalTek/Q2.5-Coldbrew14B-FusionMix SvalTek/Q2.5-Coldbrew14B-FusionMix
Model Size	15b
Required VRAM	29.7 GB
Updated	2026-04-20
Maintainer	SvalTek
Model Type	qwen2
Model Files	4.9 GB: 1-of-6 5.0 GB: 2-of-6 5.0 GB: 3-of-6 5.0 GB: 4-of-6 5.0 GB: 5-of-6 4.8 GB: 6-of-6
Supported Languages	en
Model Architecture	Qwen2ForCausalLM
License	apache-2.0
Context Length	131072
Model Max Length	131072
Transformers Version	4.56.1
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	151665
Errors	replace

Rank the Q2.5 ColdBrew 15B Oxford 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 Q2.5 ColdBrew 15B Oxford

Best Alternatives	Context / RAM	Downloads	Likes
Qwen25 15B SFT Best Again	32K / 3.1 GB	12	0
ECE MIRAGE 1 15B	32K / 61 GB	11	1