Everlier

@Everlier

Building LLM agents & tools. Local inference will win. github.com/av/harbor Also: Facts / Mi / Skilled / Pace @viktor_com

Pinned
Everlier
@Everlier
Mar 20
You don't even need Kimi 2.5 for a decent local LLM setup. - llama.cpp - Unsloth's Qwen 3.5 35B A3B with UD Q4 K XL quants - OpenCode - av/harbor It'll take a while to download/install, but otherwise it's something that mid-range hardware (>32GB RAM, ~8GB VRAM) can run today.
fynn
@fynnso
Mar 19
was messing with the OpenAI base URL in Cursor and caught this accounts/anysphere/models/kimi-k2p5-rl-0317-s515-fast so composer 2 is just Kimi K2.5 with RL at least rename the model ID
16
Build in Public
Everlier
@Everlier
7h
How you see your code
Build in Public
Everlier
@Everlier
12h
Claude Code workflows, but they work in any harness with any model, check my workgraph skill :) github.com/av/skills/tree…
Everlier
@Everlier
14h
Intelligence compute pareto frontier. Qwen 3.8 Flash Next is quite a drastic step on the chart, and it's perfect for unified memory devices. You can run it today if you have a DGX Spark, Strix Halo (Ryzen AI 395+), or a relatively recent Apple device with 64GB+ memory. Try it
1
Everlier
@Everlier
Aug 30
iykyk