What are the hardware requirements for K2 Horizon MoVA 36B A4B MLX 4bit?

K2 Horizon MoVA 36B A4B MLX 4bit requires approximately 15.6 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 MLX 4bit and how large is it?

K2 Horizon MoVA 36B A4B MLX 4bit is developed by abenzerps, 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 MLX 4bit?

K2 Horizon MoVA 36B A4B MLX 4bit 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 MLX 4bit by abenzerps — VRAM 15.6GB, 512K context

Name: K2 Horizon MoVA 36B A4B MLX 4bit
Author: abenzerps

K2 Horizon MoVA 36B A4B MLX 4bit is an open-source language model by abenzerps. Features: 36b LLM, VRAM: 15.6GB, Context: 512K, License: apache-2.0, Quantized, LLM Explorer Score: 0.33.

4-bit 4bit 512k-context Base model:ifm/k2-horizon-mova... Base model:quantized:ifm/k2-ho... Conversational Custom code En K2-horizon K2 horizon mova Long-context Mixture-of-experts Mlx Mlx-lm Mova Quantized Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/abenzerps/K2-Horizon-MoVA-36B-A4B-MLX-4bit

K2 Horizon MoVA 36B A4B MLX 4bit Parameters and Internals

LLM Name	K2 Horizon MoVA 36B A4B MLX 4bit
Repository 🤗	https://huggingface.co/abenzerps/K2-Horizon-MoVA-36B-A4B-MLX-4bit
Base Model(s)	K2 Horizon MoVA 36B A4B IFM/K2-Horizon-MoVA-36B-A4B
Model Size	36b
Required VRAM	15.6 GB
Updated	2026-09-08
Maintainer	abenzerps
Model Type	k2_horizon_mova
Model Files	0.0 GB: 1-of-48 0.0 GB: 2-of-48 0.0 GB: 3-of-48 0.4 GB: 4-of-48 0.4 GB: 5-of-48 0.4 GB: 6-of-48 0.4 GB: 7-of-48 0.4 GB: 8-of-48 0.4 GB: 9-of-48 0.4 GB: 10-of-48 0.4 GB: 11-of-48 0.4 GB: 12-of-48 0.4 GB: 13-of-48 0.4 GB: 14-of-48 0.4 GB: 15-of-48 0.4 GB: 16-of-48 0.4 GB: 17-of-48 0.4 GB: 18-of-48 0.4 GB: 19-of-48 0.4 GB: 20-of-48 0.4 GB: 21-of-48 0.4 GB: 22-of-48 0.4 GB: 23-of-48 0.4 GB: 24-of-48 0.4 GB: 25-of-48 0.4 GB: 26-of-48 0.4 GB: 27-of-48 0.4 GB: 28-of-48 0.4 GB: 29-of-48 0.4 GB: 30-of-48 0.4 GB: 31-of-48 0.4 GB: 32-of-48 0.4 GB: 33-of-48 0.4 GB: 34-of-48 0.4 GB: 35-of-48 0.4 GB: 36-of-48 0.4 GB: 37-of-48 0.4 GB: 38-of-48 0.4 GB: 39-of-48 0.4 GB: 40-of-48 0.4 GB: 41-of-48 0.4 GB: 42-of-48
Supported Languages	en
Quantization Type	4bit
Model Architecture	K2HorizonForCausalLM
License	apache-2.0
Context Length	524288
Model Max Length	524288
Transformers Version	5.13.0
Vocabulary Size	250624

Rank the K2 Horizon MoVA 36B A4B 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

Best Alternatives to K2 Horizon MoVA 36B A4B MLX 4bit

Best Alternatives	Context / RAM	Downloads	Likes
K2 Horizon MoVA 36B A4B	512K / 63 GB	433	139
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 GPTQ Int4	512K / 21.8 GB	30	1

Note: green Score (e.g. "73.2") means that the model is better than abenzerps/K2-Horizon-MoVA-36B-A4B-MLX-4bit.