# Which is the best open model for \[Julia\] coding? And practical, and still reasonably good

**URL:** <https://discourse.julialang.org/t/which-is-the-best-open-model-for-julia-coding-and-practical-and-still-reasonably-good/138640>\
**Category:** General Usage\
**Created:** [August 6, 2026, 12:35pm UTC](https://discourse.julialang.org/t/which-is-the-best-open-model-for-julia-coding-and-practical-and-still-reasonably-good/138640 "2026-08-06T12:35:21Z")\
**Posts on this page:** 1\
**Showing post:** 8

<div class="post-metadata">

**Author:** ![j\_u](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/j_u/32/219081_2.png) [@j\_u](https://discourse.julialang.org/u/j_u)\
**Post date:** [August 6, 2026, 10:09pm UTC](https://discourse.julialang.org/t/which-is-the-best-open-model-for-julia-coding-and-practical-and-still-reasonably-good/138640/8 "2026-08-06T22:09:28Z")

</div>

> [@sdanisch](#):
>
> Kimi k3 seems to do pretty well compared to opus!

_Locally_, I guess those kinds of things are _only possible_ in Germany. :- ) But seriously, how are you running it, @sdanisch? The `vLLM` requirement seems to be v0.27.0, but v0.26.0 is currently the latest official release.

@Palli, one thing I’d like to add: I have `ReactantServer.jl` on my waitlist. This looks like a huge deal:

> [@Wired: Python Is So Slow. Can Julia Solve the Two-Language Problem?](https://discourse.julialang.org/t/wired-python-is-so-slow-can-julia-solve-the-two-language-problem/138165/3):
>
> Reactant has gotten to the point where I’m using it for all of my ML training and serving, often seeing large speedups relative to PyTorch (2x to as high as 10x on the same hardware).

EDIT: Just to be clear, to mitigate any problems. The first sentence is harmless. It’s positive. A kind of a regional “smile” / “joke” / “pun”.

---

_[View the full topic](https://discourse.julialang.org/t/which-is-the-best-open-model-for-julia-coding-and-practical-and-still-reasonably-good/138640)._