What are the hardware requirements for Breeze 13B 32K Base V1.0?

Breeze 13B 32K Base V1.0 requires approximately 25.6 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 Breeze 13B 32K Base V1.0 and how large is it?

Breeze 13B 32K Base V1.0 is developed by win10, a model with 13b 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 Breeze 13B 32K Base V1.0?

Breeze 13B 32K Base V1.0 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Breeze 13B 32K Base V1.0 by win10 — VRAM 25.6GB, 32K context

Name: Breeze 13B 32K Base V1.0
Author: win10

Breeze 13B 32K Base V1.0 is an open-source language model by win10. Features: 13b LLM, VRAM: 25.6GB, Context: 32K, License: apache-2.0, Merged, LLM Explorer Score: 0.13.

Merged Model Endpoints compatible Mediatek-research/breeze-7b-32... Mistral Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/win10/Breeze-13B-32k-Base-v1_0

Breeze 13B 32K Base V1.0 Parameters and Internals

Model Type

merge

Additional Notes

The model Breeze-13B-32k-Base-v1_0 is a result of merging several instances of the model MediaTek-Research/Breeze-7B-32k-Base-v1_0 using mergekit with the passthrough merge method.

LLM Name	Breeze 13B 32K Base V1.0
Repository 🤗	https://huggingface.co/win10/Breeze-13B-32k-Base-v1_0
Merged Model	Yes
Model Size	13b
Required VRAM	25.6 GB
Updated	2026-07-17
Maintainer	win10
Model Type	mistral
Model Files	0.5 GB: 1-of-27 0.9 GB: 2-of-27 0.9 GB: 3-of-27 1.0 GB: 4-of-27 1.0 GB: 5-of-27 1.0 GB: 6-of-27 0.9 GB: 7-of-27 1.0 GB: 8-of-27 1.0 GB: 9-of-27 1.0 GB: 10-of-27 1.0 GB: 11-of-27 1.0 GB: 12-of-27 1.0 GB: 13-of-27 1.0 GB: 14-of-27 1.0 GB: 15-of-27 1.0 GB: 16-of-27 1.0 GB: 17-of-27 1.0 GB: 18-of-27 0.9 GB: 19-of-27 1.0 GB: 20-of-27 1.0 GB: 21-of-27 1.0 GB: 22-of-27 1.0 GB: 23-of-27 1.0 GB: 24-of-27 1.0 GB: 25-of-27 1.0 GB: 26-of-27 0.5 GB: 27-of-27
Model Architecture	MistralForCausalLM
License	apache-2.0
Context Length	32768
Model Max Length	32768
Transformers Version	4.41.2
Tokenizer Class	LlamaTokenizer
Padding Token	</s>
Vocabulary Size	62464
Torch Data Type	bfloat16

Rank the Breeze 13B 32K Base V1.0 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 Breeze 13B 32K Base V1.0

Best Alternatives	Context / RAM	Downloads	Likes
LuminRP 13B 128K V0.5	128K / 25.1 GB	9	2
Breeze 13B 32K Instruct V1.0	32K / 25.6 GB	8	0
Power WizardLM 2 13B	32K / 25 GB	16	2
Mistral V0.3 13B 32K Base V1	32K / 25.2 GB	7	0
Pandora 13B V1	32K / 24.9 GB	95	2
Pandora V1 13B	32K / 24.9 GB	5	3
BigMistral 13B GLUED	32K / 26.6 GB	15	1
BigMistral 13B	32K / 26.7 GB	1	2
...stral 13B DARE Blended FAILURE	32K / 26.7 GB	6	0
...stral 13B DARE Blended FAILURE	32K / 26.7 GB	5	0

Note: green Score (e.g. "73.2") means that the model is better than win10/Breeze-13B-32k-Base-v1_0.