Dev Radar
Support
LiveUpdated 2026-09-19 21:10 UTC

beellama.cpp

beellama.cpp — Tested on 2x3090, Qwen 3.8 27B UD-Q4_K_M, using prebuilts for Windows from GitHub

beellama.cpp is Tested on 2x3090, Qwen 3.8 27B UD-Q4_K_M, using prebuilts for Windows from GitHub. It is ranked #1573 on the Dev Radar, in AI dev tools, first seen 19 days ago and shared in 4 posts (2.6k views).

Visit github.com

What beellama.cpp says about itself

KVarN, KV cache precision tail, low-bit quants in llama.cpp for longer context of better precision in the same VRAM - Anbeeld/beellama.cpp

GitHub - Anbeeld/beellama.cpp at v0.4.5 · GitHub Skip to content Navigation Menu Sign in Appearance settings Search / Sign in Sign up Appearance settings You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session. You switched accounts on another tab or window. Reload to refresh your session. Dismiss alert {{ message }} Anbeeld / beellama.cpp Public forked from ggml-org/llama.cpp Uh oh! There was an error while loading. Please reload this page . Notifications You must be signed in to change notification settings Fork 74 Star 1.1k v0.4.5 Branches Tags Go…

What people said about beellama.cpp on X

BeeLlama v0.4.6 is out. A smaller release this time, just an upstream merge and a few fixes. https://github.com/Anbeeld/beellama.cpp/releases/tag/v0.4.6

@Anbeeld, 11 days ago · 11 likes · see the post

BeeLlama.cpp v0.4.5 is out. This release is heavily focused on pushing KVarN further, both in performance and where it can be used. Main changes: - Major CUDA KVarN optimizations for decode and speculative verification - KVarN support for speculative decoding: MTP, DFlash, EAGLE3, DSpark - KVarN support for Gemma 4…

@Anbeeld, 13 days ago · 5 likes · see the post

KVarN is not just optimized on CUDA as of BeeLlama v0.4.5, it's now faster than standard llama.cpp KV cache quants. Tested on 2x3090, Qwen 3.8 27B UD-Q4_K_M, using prebuilts for Windows from GitHub: https://github.com/Anbeeld/beellama.cpp/releases

@Anbeeld, 12 days ago · 4 likes · see the post

Alternatives to beellama.cpp

beellama.cpp in numbers

FAQ

What is beellama.cpp?

Tested on 2x3090, Qwen 3.8 27B UD-Q4_K_M, using prebuilts for Windows from GitHub It was first shared on X 19 days ago and is ranked #1573 on the Dev Radar.

Is beellama.cpp free?

It is open source.

Who shared beellama.cpp?

1 account on X, including @Anbeeld, in 4 posts totalling 2.6k 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. 14.4k posts from 4.7k X accounts over the last 21 days, 1.6k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-19 21:10 UTC. Full method.