What are the hardware requirements for K2 Horizon MoVA 36B A4B OQ4e?

K2 Horizon MoVA 36B A4B OQ4e requires approximately 22 GB of VRAM and supports a context window of 512K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed K2 Horizon MoVA 36B A4B OQ4e and how large is it?

K2 Horizon MoVA 36B A4B OQ4e is developed by mlx-community, a model with 36b 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 K2 Horizon MoVA 36B A4B OQ4e?

K2 Horizon MoVA 36B A4B OQ4e is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

K2 Horizon MoVA 36B A4B OQ4e by mlx-community — VRAM 22GB, 512K context

Name: K2 Horizon MoVA 36B A4B OQ4e
Author: mlx-community

K2 Horizon MoVA 36B A4B OQ4e is an open-source language model by mlx-community. Features: 36b LLM, VRAM: 22GB, Context: 512K, License: apache-2.0, LLM Explorer Score: 0.31.

4-bit Apple-silicon Base model:ifm/k2-horizon-mova... Base model:quantized:ifm/k2-ho... Conversational Custom code K2 horizon Mlx Oq Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/mlx-community/K2-Horizon-MoVA-36B-A4B-oQ4e

K2 Horizon MoVA 36B A4B OQ4e Parameters and Internals

LLM Name	K2 Horizon MoVA 36B A4B OQ4e
Repository 🤗	https://huggingface.co/mlx-community/K2-Horizon-MoVA-36B-A4B-oQ4e
Base Model(s)	K2 Horizon MoVA 36B A4B IFM/K2-Horizon-MoVA-36B-A4B
Model Size	36b
Required VRAM	22 GB
Updated	2026-09-15
Maintainer	mlx-community
Model Type	k2_horizon
Model Files	5.1 GB: 1-of-5 5.0 GB: 2-of-5 5.0 GB: 3-of-5 5.0 GB: 4-of-5 1.9 GB: 5-of-5
Model Architecture	K2HorizonForCausalLM
License	apache-2.0
Context Length	524288
Model Max Length	524288
Transformers Version	5.13.0
Tokenizer Class	PreTrainedTokenizerFast
Vocabulary Size	250624

Rank the K2 Horizon MoVA 36B A4B 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 K2 Horizon MoVA 36B A4B OQ4e

Best Alternatives	Context / RAM	Downloads	Likes
K2 Horizon MoVA 36B A4B	512K / 63 GB	433	139
...2 Horizon MoVA 36B A4B Heretic	512K / 74.9 GB	210	1
K2 Horizon MoVA 36B A4B FP8	512K / 40.6 GB	129	6
...n MoVA 36B A4B Mixed NVFP4 FP8	512K / 44.5 GB	81	1
... Horizon MoVA 36B A4B MLX 4bit	512K / 15.6 GB	692	3
...orizon MoVA 36B A4B Uncensored	512K / 63 GB	118	0
...Horizon MoVA 36B A4B GPTQ Int4	512K / 21.8 GB	30	1

Note: green Score (e.g. "73.2") means that the model is better than mlx-community/K2-Horizon-MoVA-36B-A4B-oQ4e.