LLM EXPLORER 59,420 MODELS INDEXED

Qwen2 72B Bnb 4bit by unsloth

By unsloth · 99 downloads
HF Repo ↗ Copy URL

Qwen2 72B Bnb 4bit is an open-source language model by unsloth. Features: 72b LLM, VRAM: 41.2GB, Context: 128K, License: apache-2.0, Quantized, LLM Explorer Score: 0.13.

  4-bit   4bit   Bitsandbytes   Conversational   En   Endpoints compatible   Quantized   Qwen2   Region:us   Safetensors   Sharded   Tensorflow   Unsloth
Model Card on HF 🤗: https://huggingface.co/unsloth/Qwen2-72B-bnb-4bit 

Qwen2 72B Bnb 4bit Parameters and Internals

Model Type 
transformers
Additional Notes 
The model can be fine-tuned using Google Colab with Tesla T4 for different versions like Qwen2 7b, Qwen2 0.5b, and Qwen2 1.5b. This finetuning can be done faster and with less memory usage using Unsloth.
LLM NameQwen2 72B Bnb 4bit
Repository 🤗https://huggingface.co/unsloth/Qwen2-72B-bnb-4bit 
Model Size72b
Required VRAM41.2 GB
Updated2026-07-17
Maintainerunsloth
Model Typeqwen2
Model Files  6.9 GB: 1-of-6   7.0 GB: 2-of-6   6.9 GB: 3-of-6   6.9 GB: 4-of-6   7.0 GB: 5-of-6   6.5 GB: 6-of-6
Supported Languagesen
Quantization Type4bit
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length131072
Model Max Length131072
Transformers Version4.44.2
Tokenizer ClassQwen2Tokenizer
Padding Token<|PAD_TOKEN|>
Vocabulary Size152064
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Qwen2 72B Bnb 4bit

Best Alternatives
Context / RAM
Downloads
Likes
Kimi Dev 72B 4bit DWQ128K / 40.9 GB446521
Kimi Dev 72B 8bit128K / 77.1 GB3612
Kimi Dev 72B 5bit128K / 50.1 GB3682
Qwen2.5 72B Bnb 4bit128K / 41.4 GB1531
...in 2.9.2 Qwen2 72B 6.0bpw EXL2128K / 56.1 GB51
...Qwen2 72B 4 0bpw H6 EXL2 Pippa128K / 38.6 GB71
...phin 292 Qwen2 72b EXL2 4 0bpw128K / 38.6 GB41
Qwen2 72B 4bit128K / 40.9 GB510
...n 2.9.2 Qwen72b 8.0bpw H8 EXL2128K / 66.8 GB32
...B Instruct 2.0bpw H Novel EXL2125K / 23 GB41
Note: green Score (e.g. "73.2") means that the model is better than unsloth/Qwen2-72B-bnb-4bit.