What are the hardware requirements for Inkling Mlx 4bit?

Inkling Mlx 4bit requires approximately 391.9 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Inkling Mlx 4bit and how large is it?

Inkling Mlx 4bit is developed by mlx-community, a model with 164.3b 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 Inkling Mlx 4bit?

Inkling Mlx 4bit is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Inkling Mlx 4bit by mlx-community — VRAM 391.9GB

Name: Inkling Mlx 4bit
Author: mlx-community

Inkling Mlx 4bit is an open-source language model by mlx-community. Features: 164.3b LLM, VRAM: 391.9GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.29.

4bit Base model:finetune:thinkingma... Base model:thinkingmachines/in... Conversational Inkling Inkling mm model Mlx Moe Quantized Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/mlx-community/Inkling-mlx-4bit

Inkling Mlx 4bit Parameters and Internals

LLM Name	Inkling Mlx 4bit
Repository 🤗	https://huggingface.co/mlx-community/Inkling-mlx-4bit
Base Model(s)	Inkling thinkingmachines/Inkling
Model Size	164.3b
Required VRAM	391.9 GB
Updated	2026-07-19
Maintainer	mlx-community
Model Type	inkling_mm_model
Model Files	5.0 GB: 1-of-66 5.2 GB: 2-of-66 8.3 GB: 3-of-66 8.7 GB: 4-of-66 8.7 GB: 5-of-66 8.7 GB: 6-of-66 8.7 GB: 7-of-66 8.7 GB: 8-of-66 8.6 GB: 9-of-66 8.7 GB: 10-of-66 8.7 GB: 11-of-66 8.7 GB: 12-of-66 8.7 GB: 13-of-66 8.7 GB: 14-of-66 8.7 GB: 15-of-66 8.6 GB: 16-of-66 8.7 GB: 17-of-66 8.7 GB: 18-of-66 8.7 GB: 19-of-66 8.7 GB: 20-of-66 8.7 GB: 21-of-66 8.6 GB: 22-of-66 8.7 GB: 23-of-66 8.7 GB: 24-of-66 8.7 GB: 25-of-66 8.7 GB: 26-of-66 8.7 GB: 27-of-66 8.7 GB: 28-of-66 8.6 GB: 29-of-66 8.7 GB: 30-of-66 8.7 GB: 31-of-66 8.7 GB: 32-of-66 8.7 GB: 33-of-66 8.7 GB: 34-of-66 8.7 GB: 35-of-66 8.6 GB: 36-of-66 8.7 GB: 37-of-66 8.7 GB: 38-of-66 8.7 GB: 39-of-66 8.7 GB: 40-of-66 8.7 GB: 41-of-66 8.6 GB: 42-of-66 8.7 GB: 43-of-66 8.7 GB: 44-of-66 8.6 GB: 45-of-66 8.7 GB: 46-of-66
Quantization Type	4bit
Model Architecture	InklingForConditionalGeneration
License	apache-2.0

Rank the Inkling Mlx 4bit 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