diff --git a/aider/website/_data/quant.yml b/aider/website/_data/quant.yml
index 59b70c2e1..b852a1ea5 100644
--- a/aider/website/_data/quant.yml
+++ b/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 weights via glhf.chat
+  model: HuggingFace BF16 via glhf.chat
   released: 2024-11-12
   edit_format: diff
   commit_hash: ec9982a
@@ -22,9 +22,32 @@
   seconds_per_case: 22.5
   total_cost: 0.0000
 
+- dirname: 2024-11-22-14-53-26--hyperbolic-qwen25coder32binstruct
+  test_cases: 133
+  model: Hyperbolic Qwen2.5-Coder-32B-Instruct BF16
+  edit_format: diff
+  commit_hash: f9ef161, 17aef7b-dirty
+  pass_rate_1: 57.9
+  pass_rate_2: 69.2
+  percent_cases_well_formed: 91.7
+  error_outputs: 30
+  num_malformed_responses: 29
+  num_with_malformed_responses: 11
+  user_asks: 9
+  lazy_comments: 0
+  syntax_errors: 4
+  indentation_errors: 0
+  exhausted_context_windows: 0
+  test_timeouts: 2
+  command: aider --model openai/Qwen/Qwen2.5-Coder-32B-Instruct --openai-api-base https://api.hyperbolic.xyz/v1/
+  date: 2024-11-22
+  versions: 0.64.2.dev
+  seconds_per_case: 33.2
+  total_cost: 0.0000
+  
 - dirname: 2024-11-20-15-17-37--qwen25-32b-or-diff
   test_cases: 133
-  model: openrouter/qwen/qwen-2.5-coder-32b-instruct
+  model: openrouter/qwen/qwen-2.5-coder-32b-instruct (mixed quants)
   edit_format: diff
   commit_hash: e917424
   pass_rate_1: 49.6
@@ -67,3 +90,4 @@
   versions: 0.64.2.dev
   seconds_per_case: 86.7
   total_cost: 0.0000
+
diff --git a/aider/website/_posts/2024-11-21-quantization.md b/aider/website/_posts/2024-11-21-quantization.md
index 18588e4df..087b6749c 100644
--- a/aider/website/_posts/2024-11-21-quantization.md
+++ b/aider/website/_posts/2024-11-21-quantization.md
@@ -24,6 +24,17 @@ and local model servers like Ollama.
 {% include quant-chart.js %}
 </script>
 
+The graph above compares 4 different versions of the Qwen 2.5 Coder 32B Instruct model,
+served both locally and from cloud providers.
+
+- The [HuggingFace BF16 weights](https://huggingface.co/Qwen/Qwen2.5-Coder-32B-Instruct) served via [glhf.chat](https://glhf.chat).
+- Hyperbolic labs API for [qwen2-5-coder-32b-instruct](https://app.hyperbolic.xyz/models/qwen2-5-coder-32b-instruct), which is using BF16. This result is probably within the expected variance of the HF result.
+- The results from [OpenRouter's mix of providers](https://openrouter.ai/qwen/qwen-2.5-coder-32b-instruct/providers) which serve the model with different levels of quantization.
+- Ollama locally serving [qwen2.5-coder:32b-instruct-q4_K_M)](https://ollama.com/library/qwen2.5-coder:32b-instruct-q4_K_M), which has `Q4_K_M` quantization.
+
+The best version of the model rivals GPT-4o, while the worst performer
+is more like GPT-3.5 Turbo level.
+
 <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;">
@@ -84,16 +95,6 @@ document.getElementById('quantSearchInput').addEventListener('keyup', function()
 });
 </script>
 
-The graph above compares 4 different versions of the Qwen 2.5 Coder 32B Instruct model,
-served both locally and from cloud providers.
-
-- The [HuggingFace weights](https://huggingface.co/Qwen/Qwen2.5-Coder-32B-Instruct) served via [glhf.chat](https://glhf.chat).
-- Hyperbolic labs API for [qwen2-5-coder-32b-instruct](https://app.hyperbolic.xyz/models/qwen2-5-coder-32b-instruct), which has BF16 quantization.
-- The results from [OpenRouter's mix of providers](https://openrouter.ai/qwen/qwen-2.5-coder-32b-instruct/providers) which serve the model with different levels of quantization.
-- Ollama locally serving [qwen2.5-coder:32b-instruct-q4_K_M)](https://ollama.com/library/qwen2.5-coder:32b-instruct-q4_K_M), which has `Q4_K_M` quantization.
-
-The best version of the model rivals GPT-4o, while the worst performer
-is more like GPT-3.5 Turbo level.
 
 ## Choosing providers with OpenRouter