LLM EXPLORER 59,420 MODELS INDEXED

Breeze 7B Instruct V1.0 AWQ by YC-Chen

By YC-Chen · 14 downloads
HF Repo ↗ Copy URL

Breeze 7B Instruct V1.0 AWQ is an open-source language model by YC-Chen. Features: 7b LLM, VRAM: 4.6GB, Context: 32K, Quantized, Instruction-Based, LLM Explorer Score: 0.13, Arc: 61.4, HellaSwag: 82.6, MMLU: 62.1, GSM8K: 43.1.

  4-bit   Awq   Conversational   Endpoints compatible   Instruct   Mistral   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/YC-Chen/Breeze-7B-Instruct-v1_0-AWQ 

Breeze 7B Instruct V1.0 AWQ Parameters and Internals

LLM NameBreeze 7B Instruct V1.0 AWQ
Repository 🤗https://huggingface.co/YC-Chen/Breeze-7B-Instruct-v1_0-AWQ 
Base Model(s)  Breeze 7B Instruct V1.0   MediaTek-Research/Breeze-7B-Instruct-v1_0
Model Size7b
Required VRAM4.6 GB
Updated2026-08-04
MaintainerYC-Chen
Model Typemistral
Instruction-BasedYes
Model Files  4.6 GB
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureMistralForCausalLM
Context Length32768
Model Max Length32768
Transformers Version4.38.2
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size61952
Torch Data Typefloat16

Best Alternatives to Breeze 7B Instruct V1.0 AWQ

Best Alternatives
Context / RAM
Downloads
Likes
Mistral 7B Instruct V0.2 AWQ32K / 4.2 GB60
Mistral 7B Instruct V0.2 AWQ32K / 4.2 GB29818252
Mistral 7B Instruct V0.3 AWQ32K / 4.2 GB563310
Mistral 7B Instruct V0.1 AWQ32K / 4.2 GB154612
...reeze 7B 32K Instruct V1.0 AWQ32K / 4.7 GB90
Breeze 7B Instruct V1.0 AWQ32K / 4.6 GB50
Mistral 7B Instruct V0.3 AWQ32K / 4.2 GB6281
Mistral 7B Instruct V0.3 AWQ32K / 4.2 GB50
...Instruct V0.2 AWQ 4bit Smashed32K / 4.2 GB81
Mistral 7B Instruct 32K AWQ32K / 4.2 GB41
Note: green Score (e.g. "73.2") means that the model is better than YC-Chen/Breeze-7B-Instruct-v1_0-AWQ.