What are the hardware requirements for Kimi VL A3B Thinking 8bit?

Kimi VL A3B Thinking 8bit requires approximately 17.8 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Kimi VL A3B Thinking 8bit and how large is it?

Kimi VL A3B Thinking 8bit is developed by mlx-community, a model with 1b parameters. 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 Kimi VL A3B Thinking 8bit?

Kimi VL A3B Thinking 8bit is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Kimi VL A3B Thinking 8bit by mlx-community — VRAM 17.8GB

Name: Kimi VL A3B Thinking 8bit
Author: mlx-community

Kimi VL A3B Thinking 8bit is an open-source language model by mlx-community. Features: 1b LLM, VRAM: 17.8GB, License: other, Quantized, Instruction-Based, LLM Explorer Score: 0.19.

8bit Base model:finetune:opengvlab/... Base model:opengvlab/internvl3... Conversational Custom code Dataset:opengvlab/mmpr-v1.2 Feature-extraction Image-text-to-text Instruct Internvl Kimi vl Mlx Multilingual Quantized Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/mlx-community/Kimi-VL-A3B-Thinking-8bit

Kimi VL A3B Thinking 8bit Parameters and Internals

LLM Name	Kimi VL A3B Thinking 8bit
Repository 🤗	https://huggingface.co/mlx-community/Kimi-VL-A3B-Thinking-8bit
Base Model(s)	InternVL3 1B Instruct OpenGVLab/InternVL3-1B-Instruct
Model Size	1b
Required VRAM	17.8 GB
Updated	2026-08-08
Maintainer	mlx-community
Model Type	kimi_vl
Instruction-Based	Yes
Model Files	5.2 GB: 1-of-4 5.4 GB: 2-of-4 5.2 GB: 3-of-4 2.0 GB: 4-of-4
Quantization Type	8bit
Model Architecture	KimiVLForConditionalGeneration
License	other
Model Max Length	1048576
Transformers Version	4.52.0.dev0
Padding Token	[PAD]
Vocabulary Size	163840

Rank the Kimi VL A3B Thinking 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 Kimi VL A3B Thinking 8bit

Best Alternatives	Context / RAM	Downloads	Likes
Kimi VL A3B Thinking 6bit	0K / 13.9 GB	250	1