Why “unsloth” is being discussed
The most recent Hacker News stories and comments contributing to this topic's mentions.
I have to concur with you here because I'm running 3.8-flash-next in the largest unsloth Q8 version on a 256GB system for daily use, and I've recently compared it head to head v…
by walrus01 · Oct 5, 2026
Unsloth documented the vision components degrading more during quantization for one of the earlier Qwen models.
by dr_kiszonka · Oct 5, 2026
125b at q2 is ~80gb 27b at q4 is ~16gb So from a raw amount of data, qwen3.8-flash-next wins easily. But flash-next is an MoE model, so it only has 6b parameters active per toke…
by kennywinker · Oct 4, 2026
I have fairly limited HW, so i tried standard llama-cpp and qwen3.8-flash-next, unsloth quants. Q1 was producing some garbage at times, generating wrong urls on webfetch, then c…
by Luker88 · Oct 4, 2026
That's quite the statement - unsloth quants are amazing.
by dotancohen · Oct 2, 2026
not my experience the ds4 quants were very good beating the unsloth quants https://github.com/michaelasper/benchmarks/blob/main/deepsee...
by c0rruptbytes · Oct 2, 2026
Interest
Proportion of Hacker News items mentioning "unsloth" over time.
Mentions
Total number of Hacker News items mentioning "unsloth" over time.