I

K2 Horizon MoVA 36B A4B

Sep 2026
IK2 Horizon MoVA 36B A4B
Compare in
on
—per task?
$1 / $4per 1M in / out?
—output speed?
524Kcontext

Alternatives?

Run it yourself

estimate
Fits on✗ 8 GB (phone, laptop)✗ 16 GB✓ 24 GB GPU · compressed✓ 48 GB GPU · 8-bit✓ 80 GB GPU · full quality
LicenceApache-2.0free for commercial use

FAQ

How much does K2 Horizon MoVA 36B A4B cost?›

$1 per 1M input tokens and $4 per 1M output tokens (cheapest host: Featherless).

Is K2 Horizon MoVA 36B A4B free to use?›

There is no free API; the cheapest paid price is $1 per 1M input tokens. The weights are open, so you can run it yourself.

How good is K2 Horizon MoVA 36B A4B, and what is it best at?›

#106 of 334 in Chat & Knowledge, #75 of 132 in Coding, #52 of 133 in Agents & Tool Use, #90 of 133 in Vision & Documents.

Is K2 Horizon MoVA 36B A4B better than Gemini 3.8 Flash?›

On AA-Briefcase 1.1 · Elo, K2 Horizon MoVA 36B A4B scores 1,166.7 vs 1,202.6 — lower.

How can I use K2 Horizon MoVA 36B A4B?›

Through the API of Featherless.

What is the context window of K2 Horizon MoVA 36B A4B?›

524K tokens.

When was K2 Horizon MoVA 36B A4B released? Is there a newer version?›

Released 2026-09-03. It is the current version in its line.

Is K2 Horizon MoVA 36B A4B open source?›

Yes, the weights are open (Apache-2.0 licence).

Can I run K2 Horizon MoVA 36B A4B locally?›

The weights are open and can be self-hosted; hardware needs are not confirmed yet.

Can K2 Horizon MoVA 36B A4B read images?›

No, it accepts text only.

What is K2 Horizon MoVA 36B A4B?›

K2 Horizon MoVA 36B A4B is an open-weights language model from Institute of Foundation Models, released Sep 2026.

What are the best alternatives to K2 Horizon MoVA 36B A4B?›

Qwen3.8 Flash (cheaper), GPT-6 Luna (better), Qwen3.8 27B (open weights).