LLM EXPLORER 55,709 MODELS INDEXED

QVQ 72B Preview 8bit by mlx-community

By mlx-community · 22 downloads
HF Repo ↗ Copy URL

QVQ 72B Preview 8bit is an open-source language model by mlx-community. Features: 72b LLM, VRAM: 77.8GB, Context: 125K, License: other, Quantized.

  8bit Base model:finetune:qwen/qwen2...   Base model:qwen/qwen2-vl-72b   Chat   Conversational   En   Endpoints compatible   Image-text-to-text   Mlx   Quantized   Qwen2 vl   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlx-community/QVQ-72B-Preview-8bit 

QVQ 72B Preview 8bit Parameters and Internals

LLM NameQVQ 72B Preview 8bit
Repository 🤗https://huggingface.co/mlx-community/QVQ-72B-Preview-8bit 
Base Model(s)  Qwen/Qwen2-VL-72B   Qwen/Qwen2-VL-72B
Model Size72b
Required VRAM77.8 GB
Updated2026-08-08
Maintainermlx-community
Model Typeqwen2_vl
Model Files  5.3 GB: 1-of-15   5.3 GB: 2-of-15   5.2 GB: 3-of-15   5.3 GB: 4-of-15   5.3 GB: 5-of-15   5.2 GB: 6-of-15   5.3 GB: 7-of-15   5.3 GB: 8-of-15   5.2 GB: 9-of-15   5.3 GB: 10-of-15   5.3 GB: 11-of-15   5.2 GB: 12-of-15   5.3 GB: 13-of-15   5.3 GB: 14-of-15   4.0 GB: 15-of-15
Supported Languagesen
Quantization Type8bit
Model ArchitectureQwen2VLForConditionalGeneration
Licenseother
Context Length128000
Model Max Length128000
Transformers Version4.41.2
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size152064
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to QVQ 72B Preview 8bit

Best Alternatives
Context / RAM
Downloads
Likes
QVQ 72B Preview 3bit125K / 32.2 GB215
QVQ 72B Preview 4bit125K / 41.3 GB207
QVQ 72B Preview 6bit125K / 59.7 GB342
Qwen2 VL 72B Instruct 4bit32K / 41.3 GB725
Qwen2 VL 72B Instruct 8bit32K / 77.8 GB794
QVQ 72B Preview Bf16125K / 147.7 GB233
UI TARS 72B DPO32K / 147.5 GB1735158
UI TARS 72B DPO Bf1632K / 147.7 GB301
UI TARS 72B SFT Bf1632K / 147.7 GB321
UI TARS 72B SFT32K / 204.2 GB8925