LLM EXPLORER 61,405 MODELS INDEXED

Qwen2 7B Instruct AWQ by Qwen

By Qwen · 20200 downloads
HF Repo ↗ Copy URL

Qwen2 7B Instruct AWQ is an open-source language model by Qwen. Features: 7b LLM, VRAM: 5.6GB, Context: 32K, License: apache-2.0, Quantized, Instruction-Based, LLM Explorer Score: 0.17.

  Arxiv:2309.00071   4-bit   Awq Base model:quantized:qwen/qwen... Base model:qwen/qwen2-7b-instr...   Chat   Conversational   Deploy:azure   En   Endpoints compatible   Instruct   Quantized   Qwen2   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Qwen/Qwen2-7B-Instruct-AWQ 

Qwen2 7B Instruct AWQ Parameters and Internals

Model Type 
language generation, multilingual capability, coding, mathematics, reasoning
Use Cases 
Areas:
Research, Commercial applications
Additional Notes 
Supports context length up to 131,072 tokens using YARN technique.
Supported Languages 
en (high proficiency)
Training Details 
Methodology:
Supervised finetuning and direct preference optimization
Context Length:
131072
Model Architecture:
Transformer with SwiGLU activation, attention QKV bias, group query attention, and improved tokenizer.
Input Output 
Input Format:
Chat prompts
Accepted Modalities:
text
Output Format:
text
Performance Tips:
Add the rope_scaling configuration only when processing long contexts is required.
LLM NameQwen2 7B Instruct AWQ
Repository 🤗https://huggingface.co/Qwen/Qwen2-7B-Instruct-AWQ 
Base Model(s)  Qwen2 7B Instruct   Qwen/Qwen2-7B-Instruct
Model Size7b
Required VRAM5.6 GB
Updated2026-07-23
MaintainerQwen
Model Typeqwen2
Instruction-BasedYes
Model Files  4.0 GB: 1-of-2   1.6 GB: 2-of-2
Supported Languagesen
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.38.2
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size152064
Torch Data Typefloat16
Errorsreplace

Best Alternatives to Qwen2 7B Instruct AWQ

Best Alternatives
Context / RAM
Downloads
Likes
Samantha Qwen2 7B AWQ128K / 5.6 GB100
Qwen2.5 7B Instruct AWQ32K / 5.6 GB451167648
Qwen2.5 Coder 7B Instruct AWQ32K / 5.7 GB5632491
Qwen2.5 Coder 7B Instruct AWQ32K / 5.6 GB31658124
Qwen2.5 7B Instruct 1M 4bit986K / 4.3 GB44411
...wen2.5 7B Instruct 1M Bnb 4bit986K / 5.5 GB2671
Qwen2.5 7B Instruct 1M 8bit986K / 8.1 GB634
Qwen2.5 7B Instruct 1M 6bit986K / 6.2 GB522
...B Instruct 1M Unsloth Bnb 4bit986K / 7.5 GB373
Alisia 7B Instruct V1128K / 15.4 GB1142
Note: green Score (e.g. "73.2") means that the model is better than Qwen/Qwen2-7B-Instruct-AWQ.