What are the hardware requirements for Chandra 8bit?

Chandra 8bit requires approximately 9.8 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Chandra 8bit and how large is it?

Chandra 8bit is developed by mlx-community. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Chandra 8bit?

Chandra 8bit is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Chandra 8bit by mlx-community — VRAM 9.8GB

Name: Chandra 8bit
Author: mlx-community

Chandra 8bit is an open-source language model by mlx-community. Features: LLM, VRAM: 9.8GB, License: openrail, Quantized, LLM Explorer Score: 0.21.

8-bit 8bit Conversational Endpoints compatible Image-text-to-text Mlx Ocr Quantized Qwen3 vl Region:us Safetensors Sharded Tensorflow Vlm

Model Card on HF 🤗: https://huggingface.co/mlx-community/chandra-8bit

Chandra 8bit Parameters and Internals

LLM Name	Chandra 8bit
Repository 🤗	https://huggingface.co/mlx-community/chandra-8bit
Required VRAM	9.8 GB
Updated	2026-08-08
Maintainer	mlx-community
Model Type	qwen3_vl
Model Files	5.3 GB: 1-of-2 4.5 GB: 2-of-2
Quantization Type	8bit
Model Architecture	Qwen3VLForConditionalGeneration
License	openrail
Model Max Length	262144
Transformers Version	4.57.1
Padding Token	<\|endoftext\|>
Errors	replace

Rank the Chandra 8bit capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to Chandra 8bit

Best Alternatives	Context / RAM	Downloads	Likes
Chandra 4bit	0K / 5.7 GB	137	5

Note: green Score (e.g. "73.2") means that the model is better than mlx-community/chandra-8bit.