LLM EXPLORER 59,516 MODELS INDEXED

Qwen2.5 32B Instruct GPTQ Int8 by Qwen

By Qwen · 121583 downloads
HF Repo ↗ Copy URL

Qwen2.5 32B Instruct GPTQ Int8 is an open-source language model by Qwen. Features: 32b LLM, VRAM: 35.1GB, Context: 32K, License: apache-2.0, Quantized, Instruction-Based, LLM Explorer Score: 0.21.

  Arxiv:2309.00071   Arxiv:2407.10671   8-bit Base model:quantized:qwen/qwen... Base model:qwen/qwen2.5-32b-in...   Chat   Conversational   En   Endpoints compatible   Gptq   Instruct   Quantized   Qwen2   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Qwen/Qwen2.5-32B-Instruct-GPTQ-Int8 

Qwen2.5 32B Instruct GPTQ Int8 Parameters and Internals

Model Type 
causal language model
Use Cases 
Areas:
Research, Commercial applications
Applications:
Natural language processing, Coding, Mathematics, Chatbots
Primary Use Cases:
Generating long texts, Understanding structured data, Multilingual text processing
Supported Languages 
languages_supported (29 languages including Chinese, English, French, Spanish, Portuguese, German, Italian, Russian, Japanese, Korean, Vietnamese, Thai, Arabic, and more), proficiency (Multilingual support)
Training Details 
Data Sources:
various sources mentioned in the technical report
Methodology:
Pretraining & Post-training
Context Length:
131072
Model Architecture:
transformers with RoPE, SwiGLU, RMSNorm, and Attention QKV bias
Input Output 
Input Format:
Chat-based structured prompts
Accepted Modalities:
text
Output Format:
Generated text following the prompt schema with a max of 8192 tokens
Performance Tips:
Use vLLM for processing long texts; ensure proper configuration of rope scaling for long contexts
LLM NameQwen2.5 32B Instruct GPTQ Int8
Repository 🤗https://huggingface.co/Qwen/Qwen2.5-32B-Instruct-GPTQ-Int8 
Base Model(s)  Qwen/Qwen2.5-32B-Instruct   Qwen/Qwen2.5-32B-Instruct
Model Size32b
Required VRAM35.1 GB
Updated2026-07-30
MaintainerQwen
Model Typeqwen2
Instruction-BasedYes
Model Files  3.9 GB: 1-of-9   4.0 GB: 2-of-9   4.0 GB: 3-of-9   4.0 GB: 4-of-9   4.0 GB: 5-of-9   4.0 GB: 6-of-9   4.0 GB: 7-of-9   4.0 GB: 8-of-9   3.2 GB: 9-of-9
Supported Languagesen
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.39.3
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size152064
Torch Data Typefloat16
Errorsreplace

Best Alternatives to Qwen2.5 32B Instruct GPTQ Int8

Best Alternatives
Context / RAM
Downloads
Likes
Qwen2.5 32B Instruct GPTQ Int432K / 19.5 GB47852040
...5 Coder 32B Instruct GPTQ Int432K / 19.5 GB2061924
...5 Coder 32B Instruct GPTQ Int832K / 35.1 GB77124
EVA Instruct 32B EXL2 4.0128K / 17.7 GB43
....5 Coder 32B Instruct Bnb 4bit32K / 19.2 GB55196
...wen2.5 Coder 32B Instruct 3bit32K / 14.3 GB1444
Qwen 32B Incorrect Trivia 232K / 65.8 GB120
Qwen2.5 32B Instruct Bnb 4bit32K / 19.2 GB4942715
...wen2.5 Coder 32B Instruct 4bit32K / 18.5 GB235712
Cogito R132K / 65.8 GB85
Note: green Score (e.g. "73.2") means that the model is better than Qwen/Qwen2.5-32B-Instruct-GPTQ-Int8.