{"database": "hackernews", "table": "items", "rows": [[47251041, "comment", "NortySpock", 1772646082, "I managed to get qwen2.5-coder:14B working under ollama on an Nvidia 2080 Ti with 11GB of VRAM, using ollama cli, outputting what looks like 200 words-per-minute to my eye<p>It has been useful for education (&quot;What does this Elixir code do? &lt;Paste file&gt; ..... &lt;general explanation&gt; &quot;then What this line mean?&quot;)<p>as well as getting a few basic tests written when I&#x27;m unfamiliar with the syntax. (&quot;In Elixir Phoenix, given &lt;subject under test, paste entire module file&gt; and &lt;test helper module, paste entire file&gt; and &lt;existing tests, pasted in, used both for context and as examples&gt; , what is one additional test you would write?&quot;)<p>This is useful in that I get a single test I can review, run, paste in, and I&#x27;m not using any quota. Generally I have to fix it, but that&#x27;s just a matter of reading the actual test and throwing the test failure output to the LLM to propose a fix. Some human judgement is required but once I got going adding a test took 10 minutes despite being relatively unfamiliar with Elixir Phoenix .<p>It&#x27;s a nice loop, I&#x27;m in the loop, and I&#x27;m learning Elixir and contributing a useful feature that has tests.", 0, 47250015, null, null, null, null, null, 0, null, null, 1774119946494]], "columns": ["id", "type", "by", "time", "text", "dead", "parent", "poll", "url", "score", "title", "descendants", "deleted", "kids", "parts", "cached_at"], "primary_keys": ["id"], "primary_key_values": ["47251041"], "units": {}, "query_ms": 2.7746502310037613}