LLM EXPLORER 60,645 MODELS INDEXED

Breeze 13B 32K Instruct V1.0 by win10

By win10 · 8 downloads
HF Repo ↗ Copy URL

Breeze 13B 32K Instruct V1.0 is an open-source language model by win10. Features: 13b LLM, VRAM: 25.6GB, Context: 32K, License: apache-2.0, Instruction-Based, Merged, LLM Explorer Score: 0.17.

  Merged Model   Conversational   Endpoints compatible   Instruct Mediatek-research/breeze-7b-32...   Mistral   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/win10/Breeze-13B-32k-Instruct-v1_0 

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

Model Type 
merge, mergekit, lazymergekit
Additional Notes 
This model was created by merging multiple instances of the MediaTek-Research/Breeze-7B-32k-Instruct-v1_0 model using the MergeKit tool, with passthrough merging technique and specific layer range configuration.
LLM NameBreeze 13B 32K Instruct V1.0
Repository 🤗https://huggingface.co/win10/Breeze-13B-32k-Instruct-v1_0 
Merged ModelYes
Model Size13b
Required VRAM25.6 GB
Updated2026-07-23
Maintainerwin10
Model Typemistral
Instruction-BasedYes
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 ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.41.2
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size62464
Torch Data Typebfloat16