copy

aider/website/_data/quant.yml

@@ -1,6 +1,6 @@
 - dirname: 2024-11-09-11-09-15--Qwen2.5-Coder-32B-Instruct
   test_cases: 133
-  model: HuggingFace BF16 via glhf.chat
+  model: HuggingFace BF16 via GLHF
   released: 2024-11-12
   edit_format: diff
   commit_hash: ec9982a
@@ -24,7 +24,7 @@
 
 - dirname: 2024-11-22-14-53-26--hyperbolic-qwen25coder32binstruct
   test_cases: 133
-  model: Hyperbolic Qwen2.5-Coder-32B-Instruct BF16
+  model: Hyperbolic BF16
   edit_format: diff
   commit_hash: f9ef161, 17aef7b-dirty
   pass_rate_1: 57.9
@@ -47,7 +47,7 @@
   
 - dirname: 2024-11-20-15-17-37--qwen25-32b-or-diff
   test_cases: 133
-  model: openrouter/qwen/qwen-2.5-coder-32b-instruct (mixed quants)
+  model: OpenRouter (mixed)
   edit_format: diff
   commit_hash: e917424
   pass_rate_1: 49.6
@@ -70,7 +70,7 @@
 
 - dirname: 2024-11-21-23-33-47--ollama-qwen25-coder
   test_cases: 133
-  model: qwen2.5-coder:32b-instruct-q4_K_M
+  model: Ollama Q4_K_M
   edit_format: diff
   commit_hash: 488c88d-dirty
   pass_rate_1: 44.4

aider/website/_posts/2024-11-21-quantization.md

@@ -35,6 +35,10 @@ served both locally and from cloud providers.
 The best version of the model rivals GPT-4o, while the worst performer
 is more like GPT-3.5 Turbo level.
 
+{: .note }
+This article is being updated as new benchmark runs complete.
+The original version included incorrect Ollama models.
+
 <input type="text" id="quantSearchInput" placeholder="Search..." style="width: 100%; max-width: 800px; margin: 10px auto; padding: 8px; display: block; border: 1px solid #ddd; border-radius: 4px;">
 
 <table style="width: 100%; max-width: 800px; margin: auto; border-collapse: collapse; box-shadow: 0 2px 4px rgba(0,0,0,0.1); font-size: 14px;">
@@ -103,6 +107,3 @@ OpenRouter allows you to ignore specific providers in your
 This can be effective to exclude highly quantized or otherwise
 undesirable providers.
 
-{: .note }
-The original version of this article included incorrect Ollama models
-that were not Qwen 2.5 Coder 32B Instruct.