k2-horizon-mova-36b-a4b-exl3
k2-horizon-mova-36b-a4b-exl3 is We’re on a journey to advance and democratize artificial intelligence through open source and open science.. It is ranked #438 on the Dev Radar, in Other, first seen 2 h ago and shared in 2 posts (1.1k views).
vcruz305/K2-Horizon-MoVA-36B-A4B-EXL3 · Hugging Face Hugging Face Log In Sign Up vcruz305 / K2-Horizon-MoVA-36B-A4B-EXL3 Like 0 Text Generation Safetensors English exllamav3 exl3 sage k2-horizon mova Mixture of Experts License: apache-2.0 Model card Files Files and versions xet Community Copy to bucket new K2-Horizon-MoVA-36B-A4B · EXL3 EXL3 quantizations of IFM's K2-Horizon-MoVA-36B-A4B , one folder per bitrate. Every pack is scored against the BF16 original on held-out text before it is uploaded. bpw size smallest card top-1 vs BF16 mean KLD p99 KLD download 8.00 38.07 GB 96 / 48 GB 96.43% (9,874 / 10,240) 0.0047 0.042 8.00bpw 6.50 31.34…
What people said about k2-horizon-mova-36b-a4b-exl3 on X
One 36B MoE. Six EXL3 releases. GPUs from 8 GB to 96 GB. 🔥 K2-Horizon-MoVA-36B-A4B is now local for almost everyone!! 👇🏼 2.5 bpw: 13.27 GB with 83.7% top-1 agreement 8.0 bpw: 38.07 GB with 96.43% agreement, at roughly half the BF16 weight footprint This is exactly why I use EXL3 when the goal is maximum model…
— @ViC305, 2 h ago · 11 likes · see the post
The EXL3 wizard strikes again! 🧙♂️ If you want to see what peak AI optimization looks like, this is it. Running a high tier 36B MoE model locally on anything from a budget 8GB card to a 96GB monster is absolute madness by my boy @ViC305 . Data efficiency here is wild 8.0 bpw getting 96.43% agreement at half the…
— @Blackwellboy, 1 h ago · 4 likes · see the post
Alternatives to k2-horizon-mova-36b-a4b-exl3
- Spark-X2.5 — Model Scope
- qwen-image-2.1 — Qwen's most powerful open-source image generation model - QwenLM/Qwen-Image-2.1
- mimo-v2.6-flash-rl — We’re on a journey to advance and democratize artificial intelligence through open source and open science.
- openai.com —
- Omarchy — Thrilled to announce @alibaba_cloud as a Founding Corporate Patron for the Omacom Foundation! $3 million in funding,…
- mimo-v2.6-pro-rl — We’re on a journey to advance and democratize artificial intelligence through open source and open science.
k2-horizon-mova-36b-a4b-exl3 in numbers
- Rank on the Dev Radar: #438 of 2520
- Shared in 2 posts by 2 accounts: @ViC305, @Blackwellboy
- 1.1k views on those posts
- First seen 2 h ago, last shared 1 h ago
- Pricing seen by Jev: open source
- Market: Other
FAQ
What is k2-horizon-mova-36b-a4b-exl3?
We’re on a journey to advance and democratize artificial intelligence through open source and open science. It was first shared on X 2 h ago and is ranked #438 on the Dev Radar.
Is k2-horizon-mova-36b-a4b-exl3 free?
It is open source.
Who shared k2-horizon-mova-36b-a4b-exl3?
2 accounts on X, including @ViC305, @Blackwellboy, in 2 posts totalling 1.1k views.
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 22k posts from 5k X accounts over the last 21 days, 2.5k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-23 04:56 UTC. Full method.