#

#Tag

#qwen3.5-0.8b-weight-space-programming

Browse all articles tagged "qwen3.5-0.8b-weight-space-programming"

1+ posts

Modifying Only 131,072 Weights: Qwen3.5-0.8B, Whose README Claims GSM8K Jumped from 13.8% to 67.1% | On-Premise AI Lab

On-Premises AI Lab

Mark Ku

·Nov 4, 2026

Modifying Only 131,072 Weights: Qwen3.5-0.8B, Whose README Claims GSM8K Jumped from 13.8% to 67.1% | On-Premise AI Lab

Categories

Browse articles by category

#1

AI

36+ articles

DevOps thumbnail

#2

DevOps

32+ articles

Frontend thumbnail

#3

Frontend

39+ articles

Management thumbnail

Management

25+ articles

Infra thumbnail

Infra

22+ articles

PowerShell thumbnail

PowerShell

15+ articles

Travel thumbnail

Travel

12+ articles

E-Commerce thumbnail

E-Commerce

11+ articles

.NET Core thumbnail

.NET Core

11+ articles

Cloud thumbnail

Cloud

10+ articles

標籤文章

Modifying Only 131,072 Weights: Qwen3.5-0.8B, Whose README Claims GSM8K Jumped from 13.8% to 67.1% | On-Premise AI Lab

On-Premises AI Lab

Modifying Only 131,072 Weights: Qwen3.5-0.8B, Whose README Claims GSM8K Jumped from 13.8% to 67.1% | On-Premise AI Lab

Mark Ku

November 4, 2026·25 min read