249 points by de_sty 1 day ago | 108 comments | View on ycombinator
chriddyp 1 day ago |
woah 1 day ago |
pkoiralap 1 day ago |
https://huggingface.co/sabicap/sabi-noema
Also HF model here: https://huggingface.co/RadixArk/DaisyRose-27B
jacquesm 1 day ago |
xlayn 1 day ago |
"18 days on 144 H200 GPUs" insane.. didn't thought so much hardware would be needed to train Qwen.
mips_avatar 1 day ago |
potus_kushner about 15 hours ago |
octoberfranklin 1 day ago |
You might be able to shave that down using a different flavor of H200 (like PCIe) but it would take more hours, so benefits are unclear.
undefined 1 day ago |
0x69420 1 day ago |
robertkarl 1 day ago |
XCSme 1 day ago |
htrp about 18 hours ago |
DeathArrow about 23 hours ago |
For example doing backend projects using C# or Go.
DeathArrow 1 day ago |
They left a lot of performance on the table.
Which makes me wonder if such kind of optimizations are possible for other models like Deepseek v4.1 Flash 1017.
amarinhodev 1 day ago |
SparkleQwen27b about 21 hours ago |
bzvox 1 day ago |
Qwen 27B really punches above its weight. 27B is small enough to fit on a Mac Mini / Macbook Pro which is very exciting.
Starting to see more promising examples of companies post-training. From my evals [1], I've tested 3 so far:
1. Fireworks' Ember-1 (postrained on Kimi K3, improved score by 10% in my evals)
2. Particle AI's Particle-1 (fine-tuned on DeepSeek V4.1 Flash, also a 10% improvement and a bit cheaper and faster)
3. Nex AGI's Nex-N2.6 (post-trained on GLM 5.3 Flash. Didn't show an improvement in my eval, and had a couple runaway loops that made it expensive).
With Thinking Machines' western open model release (Inkling Small) a few weeks ago, I expect we'll see more of this, especially out of western companies.
[1] https://plotly.com/blog/nex-n2-6-plotly-data-analytics-bench...