LLM EXPLORER 55,709 MODELS INDEXED

Qwen2.5 VL 7B Instruct 8bit by mlx-community

By mlx-community · 1759 downloads
HF Repo ↗ Copy URL

Qwen2.5 VL 7B Instruct 8bit is an open-source language model by mlx-community. Features: 7b LLM, VRAM: 8.9GB, Context: 125K, License: apache-2.0, Quantized, Instruction-Based.

  8bit Base model:finetune:qwen/qwen2... Base model:qwen/qwen2.5-vl-7b-...   Conversational   En   Endpoints compatible   Image-text-to-text   Instruct   Mlx   Multimodal   Quantized   Qwen2 5 vl   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlx-community/Qwen2.5-VL-7B-Instruct-8bit 

Qwen2.5 VL 7B Instruct 8bit Parameters and Internals

LLM NameQwen2.5 VL 7B Instruct 8bit
Repository 🤗https://huggingface.co/mlx-community/Qwen2.5-VL-7B-Instruct-8bit 
Base Model(s)  Qwen/Qwen2.5-VL-7B-Instruct   Qwen/Qwen2.5-VL-7B-Instruct
Model Size7b
Required VRAM8.9 GB
Updated2026-08-08
Maintainermlx-community
Model Typeqwen2_5_vl
Instruction-BasedYes
Model Files  5.3 GB: 1-of-2   3.6 GB: 2-of-2
Supported Languagesen
Quantization Type8bit
Model ArchitectureQwen2_5_VLForConditionalGeneration
Licenseapache-2.0
Context Length128000
Model Max Length128000
Transformers Version4.41.2
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size152064
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Qwen2.5 VL 7B Instruct 8bit

Best Alternatives
Context / RAM
Downloads
Likes
Qwen2.5 VL 7B Instruct 3bit125K / 4.7 GB561
Jedi 7B 1080p 4bit125K / 4.9 GB191
OlmOCR 2 7B 1025 Mlx 4bit125K / 5.6 GB1261
Qwen2.5 VL 7B Instruct 4bit125K / 5.6 GB34864
Jedi 7B 1080p 6bit125K / 6.9 GB191
Qwen2.5 VL 7B Instruct 6bit125K / 6.9 GB1073
OlmOCR 2 7B 1025 Mlx 8bit125K / 9.4 GB1722
OlmOCR 7B 0725 8bit125K / 9.4 GB975
OmniLong Qwen2.5 VL 7B512K / 16.6 GB72
Qwen2.5 VL 7B Instruct FP4125K / 7.2 GB491653
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Qwen2.5-VL-7B-Instruct-8bit.