LLM EXPLORER 59,420 MODELS INDEXED

Qwen2.5 72B Instruct AWQ by Qwen

By Qwen · 1054752 downloads
HF Repo ↗ Copy URL

Qwen2.5 72B Instruct AWQ is an open-source language model by Qwen. Features: 72b LLM, VRAM: 41.6GB, Context: 32K, License: other, Quantized, Instruction-Based, LLM Explorer Score: 0.38, ELO: 1303.

  Arxiv:2309.00071   Arxiv:2407.10671   4-bit   Awq Base model:quantized:qwen/qwen... Base model:qwen/qwen2.5-72b-in...   Chat   Conversational   En   Endpoints compatible   Instruct   Quantized   Qwen2   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Qwen/Qwen2.5-72B-Instruct-AWQ 

Qwen2.5 72B Instruct AWQ Benchmarks

LMSys ELO 1303 vs 1272 (so35) 2.4%
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Qwen2.5 72B Instruct AWQ Parameters and Internals

Model Type 
Causal Language Models
Additional Notes 
The model is AWQ-quantized to 4-bit.
Supported Languages 
en (English), zh (Chinese), fr (French), es (Spanish), pt (Portuguese), de (German), it (Italian), ru (Russian), ja (Japanese), ko (Korean), vi (Vietnamese), th (Thai), ar (Arabic)
Training Details 
Context Length:
131072
Model Architecture:
transformers with RoPE, SwiGLU, RMSNorm, and Attention QKV bias
Input Output 
Accepted Modalities:
text
Performance Tips:
Use vLLM for deployment to optimize performance on lengthy texts. Add the 'rope_scaling' configuration when processing long contexts.
LLM NameQwen2.5 72B Instruct AWQ
Repository 🤗https://huggingface.co/Qwen/Qwen2.5-72B-Instruct-AWQ 
Base Model(s)  Qwen/Qwen2.5-72B-Instruct   Qwen/Qwen2.5-72B-Instruct
Model Size72b
Required VRAM41.6 GB
Updated2026-07-11
MaintainerQwen
Model Typeqwen2
Instruction-BasedYes
Model Files  3.9 GB: 1-of-11   3.9 GB: 2-of-11   4.0 GB: 3-of-11   4.0 GB: 4-of-11   3.9 GB: 5-of-11   4.0 GB: 6-of-11   4.0 GB: 7-of-11   3.9 GB: 8-of-11   4.0 GB: 9-of-11   3.5 GB: 10-of-11   2.5 GB: 11-of-11
Supported Languagesen
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureQwen2ForCausalLM
Licenseother
Context Length32768
Model Max Length32768
Transformers Version4.44.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size152064
Torch Data Typefloat16
Errorsreplace

Best Alternatives to Qwen2.5 72B Instruct AWQ

Best Alternatives
Context / RAM
Downloads
Likes
Athene V2 Chat AWQ32K / 41.6 GB644
Qwen2 72B Instruct AWQ32K / 41.6 GB161241
Qwen2 72B Instruct AWQ GEMM32K / 41.6 GB50
Typhoon V1.5 72B Instruct AWQ32K / 41.3 GB113
Typhoon V1.5 72B Instruct AWQ32K / 41.3 GB53
...B Instruct 2.0bpw H Novel EXL2125K / 23 GB41
Qwen2 72B Instruct 4bit32K / 40.9 GB562
ECE ILAB Q132K / 77.8 GB150
Qwen2.5 72B Instruct Bnb 4bit32K / 41.4 GB34708
Qwen2.5 72B Instruct 4bit32K / 40.9 GB12007