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

K2 Horizon MoVA 36B A4B requires approximately 63 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 and how large is it?

K2 Horizon MoVA 36B A4B is developed by IFM, 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?

K2 Horizon MoVA 36B A4B 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 by IFM — VRAM 63GB, 512K context

Name: K2 Horizon MoVA 36B A4B
Author: IFM

K2 Horizon MoVA 36B A4B is an open-source language model by IFM. Features: 36b LLM, VRAM: 63GB, Context: 512K, License: apache-2.0, LLM Explorer Score: 0.33.

36b Conversational Custom code Dataset:ifm/k2-horizon-midtrai... Dataset:ifm/k2-horizon-pretrai... En Ifm K2-horizon K2 horizon Moe Mova Open-weights Region:us Safetensors Sharded Tensorflow

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

K2 Horizon MoVA 36B A4B Parameters and Internals

LLM Name	K2 Horizon MoVA 36B A4B
Repository 🤗	https://huggingface.co/IFM/K2-Horizon-MoVA-36B-A4B
Model Name	K2-Horizon-MoVA-36B-A4B
Model Size	36b
Required VRAM	63 GB
Updated	2026-09-04
Maintainer	IFM
Model Type	k2_horizon
Model Files	0.2 GB: 1-of-48 0.2 GB: 2-of-48 0.2 GB: 3-of-48 1.6 GB: 4-of-48 1.6 GB: 5-of-48 1.6 GB: 6-of-48 1.6 GB: 7-of-48 1.6 GB: 8-of-48 1.6 GB: 9-of-48 1.6 GB: 10-of-48 1.6 GB: 11-of-48 1.6 GB: 12-of-48 1.6 GB: 13-of-48 1.6 GB: 14-of-48 1.6 GB: 15-of-48 1.6 GB: 16-of-48 1.6 GB: 17-of-48 1.6 GB: 18-of-48 1.6 GB: 19-of-48 1.6 GB: 20-of-48 1.6 GB: 21-of-48 1.6 GB: 22-of-48 1.6 GB: 23-of-48 1.6 GB: 24-of-48 1.6 GB: 25-of-48 1.6 GB: 26-of-48 1.6 GB: 27-of-48 1.6 GB: 28-of-48 1.6 GB: 29-of-48 1.6 GB: 30-of-48 1.6 GB: 31-of-48 1.6 GB: 32-of-48 1.6 GB: 33-of-48 1.6 GB: 34-of-48 1.6 GB: 35-of-48 1.6 GB: 36-of-48 1.6 GB: 37-of-48 1.6 GB: 38-of-48 1.6 GB: 39-of-48 1.6 GB: 40-of-48 1.6 GB: 41-of-48 1.6 GB: 42-of-48
Supported Languages	en
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 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

Quantized Models of the K2 Horizon MoVA 36B A4B

Model	Likes	Downloads	VRAM
K2 Horizon MoVA 36B A4B 4bit	3	315	26 GB
... Horizon MoVA 36B A4B MLX 4bit	3	692	15 GB
K2 Horizon MoVA 36B A4B 8bit	1	126	39 GB
...Horizon MoVA 36B A4B GPTQ Int4	1	30	21 GB

Best Alternatives to K2 Horizon MoVA 36B A4B

Best Alternatives	Context / RAM	Downloads	Likes
Jais 3 MoVA 36B A4B	512K / 149.8 GB	1569	9
K2 Horizon MoVA 36B A4B MLA	512K / 64.6 GB	536	1
...zon MoVA 36B A4B DERISKED BF16	512K / 64.6 GB	524	3
K2 Horizon MoVA 36B A4B OQ4e	512K / 22 GB	1098	2
...on MoVA 36B A4B DERISKED NVFP4	512K / 33.8 GB	242	1
...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
K2 Horizon MoVA 36B A4B 4bit	512K / 26.5 GB	315	3
... Horizon MoVA 36B A4B MLX 4bit	512K / 15.6 GB	692	3