From 5d3f2010b954d7955acd0952cc6e3e09b0a7ccec Mon Sep 17 00:00:00 2001
From: Paul Buetow
Date: Sun, 31 May 2026 18:38:40 +0300
Subject: Update content for html
---
gemfeed/2026-06-01-gt-calculator.html | 2 +-
gemfeed/atom.xml | 4 ++--
index.html | 2 +-
uptime-stats.html | 22 +++++++++++-----------
4 files changed, 15 insertions(+), 15 deletions(-)
diff --git a/gemfeed/2026-06-01-gt-calculator.html b/gemfeed/2026-06-01-gt-calculator.html
index 34697c90..97a334ba 100644
--- a/gemfeed/2026-06-01-gt-calculator.html
+++ b/gemfeed/2026-06-01-gt-calculator.html
@@ -600,7 +600,7 @@ http://www.gnu.org/software/src-highlite -->
gt on Codeberg
-But will I now invest a couple of thousand dollars in hardware to run Qwen 3.6 35B or 27B? (I used the dense 27B model most of the time to build gt). Unfortunately, no. I don't think it's worth the cost yet, as cloud models are still cheaper and more convenient and the frontier ones also much more "intelligent".
+But will I now invest a couple of thousand dollars in hardware to run Qwen 3 Coder Next, Qwen 3.6 35B or 27B? (I used the dense 27B model most of the time to build gt). Unfortunately, no. I don't think it's worth the cost yet, as cloud models are still cheaper and more convenient and the frontier ones also much more "intelligent".
However, I will keep an eye on how the technology develops and continue experimenting with rented Hyperstack VMs for now; I will also default more often to smaller LLMs that could potentially run on home hardware. Ollama Cloud subscription or an OpenRouter API key are also good options alongside Claude and OpenAI Codex.
diff --git a/gemfeed/atom.xml b/gemfeed/atom.xml
index 4c4183b1..2606a48d 100644
--- a/gemfeed/atom.xml
+++ b/gemfeed/atom.xml
@@ -1,6 +1,6 @@
- 2026-05-31T18:37:38+03:00
+ 2026-05-31T18:38:04+03:00foo.zone feedTo be in the .zone!
@@ -607,7 +607,7 @@ http://www.gnu.org/software/src-highlite -->
gt on Codeberg
-But will I now invest a couple of thousand dollars in hardware to run Qwen 3.6 35B or 27B? (I used the dense 27B model most of the time to build gt). Unfortunately, no. I don't think it's worth the cost yet, as cloud models are still cheaper and more convenient and the frontier ones also much more "intelligent".
+But will I now invest a couple of thousand dollars in hardware to run Qwen 3 Coder Next, Qwen 3.6 35B or 27B? (I used the dense 27B model most of the time to build gt). Unfortunately, no. I don't think it's worth the cost yet, as cloud models are still cheaper and more convenient and the frontier ones also much more "intelligent".
However, I will keep an eye on how the technology develops and continue experimenting with rented Hyperstack VMs for now; I will also default more often to smaller LLMs that could potentially run on home hardware. Ollama Cloud subscription or an OpenRouter API key are also good options alongside Claude and OpenAI Codex.
-This site was last updated at 2026-05-31T18:37:38+03:00
+This site was last updated at 2026-05-31T18:38:33+03:00
The following stats were collected via uptimed on all of my personal computers over many years and the output was generated by goprecords, the global uptime records stats analyser of mine.