VQV Signal

OPEN SOURCE SOURCE-BACKED TECHNICAL

Blogger benchmarks 22 local LLMs while looking for a Qwen 3.8 35B model

A blog post on sevangelatos.github.io, shared on Hacker News, describes a benchmark of 22 local LLMs. According to the headline, the author was looking for a Qwen 3.8 35B model that was not released. The Hacker News listing shows 2 points and no comments, and the snippet does not include benchmark scores or methodology.

Source: Hacker News · sevangelatos.github.io Published 2026-11-19T19:40:19+00:00 Detected 2026-11-21T16:05:28+00:00
View original source

A blog post on sevangelatos.github.io, shared on Hacker News, describes a benchmark of 22 local LLMs. According to the headline, the author was looking for a Qwen 3.8 35B model that was not released. The Hacker News listing shows 2 points and no comments, and the snippet does not include benchmark scores or methodology.

AI-assisted summary based on the listed source.

Developers who run open-source models locally may find the post useful as a comparison of 22 models, but the snippet does not show its results. Readers should check the full post for the tests used and the model versions tested. The claim about the missing Qwen model rests on the headline, so it should be confirmed against Qwen's own release announcements.

Signal Strength 94% Technical label SOURCE-BACKED Public Interest 41 Category OPEN SOURCE Reader Depth TECHNICAL

Signal Strength reflects source quality, relevance, freshness and evidence. Public Interest helps organize discovery; it is not proof of truth.

Public Interest components
Recognizable Entity Score 65 Practical Impact Score 8 Novelty Interest Score 72 Consequence Score 24 Curiosity Score 0 Shareability Score 48

VQV surfaced this signal because it is recent, relevant to Open Source LLMs, connected to Hacker News.