What are the hardware requirements for Inkling 2 Small OQ4e?

Inkling 2 Small OQ4e requires approximately 322.3 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Inkling 2 Small OQ4e and how large is it?

Inkling 2 Small OQ4e is developed by mlx-community, a model with 594.1b 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 Inkling 2 Small OQ4e?

Inkling 2 Small OQ4e is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Inkling 2 Small OQ4e by mlx-community — VRAM 322.3GB

Name: Inkling 2 Small OQ4e
Author: mlx-community

Inkling 2 Small OQ4e is an open-source language model by mlx-community. Features: 594.1b LLM, VRAM: 322.3GB, License: apache-2.0, LLM Explorer Score: 0.34.

4-bit Base model:quantized:thinkingm... Base model:thinkingmachines/in... Conversational Image-text-to-text Inkling2 Mlx Mtp Oq Quantized Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/mlx-community/Inkling-2-Small-oQ4e

Inkling 2 Small OQ4e Parameters and Internals

LLM Name	Inkling 2 Small OQ4e
Repository 🤗	https://huggingface.co/mlx-community/Inkling-2-Small-oQ4e
Base Model(s)	Inkling 2 Small thinkingmachines/Inkling-2-Small
Model Size	594.1b
Required VRAM	322.3 GB
Updated	2026-11-14
Maintainer	mlx-community
Model Type	inkling2
Model Files	7.3 GB: 1-of-49 7.0 GB: 2-of-49 7.0 GB: 3-of-49 7.0 GB: 4-of-49 7.0 GB: 5-of-49 7.0 GB: 6-of-49 7.0 GB: 7-of-49 7.0 GB: 8-of-49 7.0 GB: 9-of-49 7.0 GB: 10-of-49 7.0 GB: 11-of-49 7.0 GB: 12-of-49 7.0 GB: 13-of-49 7.0 GB: 14-of-49 7.0 GB: 15-of-49 7.0 GB: 16-of-49 7.0 GB: 17-of-49 7.0 GB: 18-of-49 7.0 GB: 19-of-49 7.0 GB: 20-of-49 7.0 GB: 21-of-49 7.0 GB: 22-of-49 7.0 GB: 23-of-49 7.0 GB: 24-of-49 7.0 GB: 25-of-49 7.0 GB: 26-of-49 7.0 GB: 27-of-49 7.0 GB: 28-of-49 7.0 GB: 29-of-49 7.0 GB: 30-of-49 7.0 GB: 31-of-49 7.0 GB: 32-of-49 7.0 GB: 33-of-49 7.0 GB: 34-of-49 7.0 GB: 35-of-49 7.0 GB: 36-of-49 7.0 GB: 37-of-49 7.0 GB: 38-of-49 7.0 GB: 39-of-49 7.0 GB: 40-of-49 7.0 GB: 41-of-49 7.0 GB: 42-of-49 7.0 GB: 43-of-49 7.0 GB: 44-of-49 7.0 GB: 45-of-49 7.0 GB: 46-of-49
Model Architecture	Inkling2ForConditionalGeneration
License	apache-2.0

Rank the Inkling 2 Small OQ4e 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 Inkling 2 Small OQ4e

Best Alternatives	Context / RAM	Downloads	Likes
Inkling 2 Small	0K / 389.9 GB	1064	219

Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Inkling-2-Small-oQ4e.