From 307c23631ab3d2d5c8c38f8bd8fb277ea9a562c6 Mon Sep 17 00:00:00 2001
From: Paul Gauthier <aider@paulg.org>
Date: Fri, 22 Nov 2024 17:20:38 -0800
Subject: [PATCH] copy

---
 aider/website/_data/quant.yml                 | 23 +++++++++++++++++++
 .../website/_posts/2024-11-21-quantization.md |  7 ++++--
 2 files changed, 28 insertions(+), 2 deletions(-)

diff --git a/aider/website/_data/quant.yml b/aider/website/_data/quant.yml
index c84755dca30..baaefa6585b 100644
--- a/aider/website/_data/quant.yml
+++ b/aider/website/_data/quant.yml
@@ -22,6 +22,29 @@
   seconds_per_case: 22.5
   total_cost: 0.0000
 
+- dirname: 2024-11-22-18-56-13--ollama-qwen2.5-coder:32b-instruct-fp16
+  test_cases: 132
+  model: ollama/qwen2.5-coder:32b-instruct-fp16 (64k context)
+  edit_format: diff
+  commit_hash: f06452c-dirty, 6a0a97c-dirty, 4e9ae16-dirty, 5506d0f-dirty
+  pass_rate_1: 58.3
+  pass_rate_2: 71.4
+  percent_cases_well_formed: 90.2
+  error_outputs: 27
+  num_malformed_responses: 26
+  num_with_malformed_responses: 13
+  user_asks: 2
+  lazy_comments: 0
+  syntax_errors: 0
+  indentation_errors: 0
+  exhausted_context_windows: 0
+  test_timeouts: 0
+  command: aider --model ollama/qwen2.5-coder:32b-instruct-fp16
+  date: 2024-11-22
+  versions: 0.64.2.dev
+  seconds_per_case: 119.6
+  total_cost: 0.0000
+  
 - dirname: 2024-11-22-14-53-26--hyperbolic-qwen25coder32binstruct
   test_cases: 133
   model: Hyperbolic BF16
diff --git a/aider/website/_posts/2024-11-21-quantization.md b/aider/website/_posts/2024-11-21-quantization.md
index 3e4ba910c29..2d8391ac56c 100644
--- a/aider/website/_posts/2024-11-21-quantization.md
+++ b/aider/website/_posts/2024-11-21-quantization.md
@@ -18,17 +18,20 @@ can strongly impact code editing skill.
 Heavily quantized models are often used by cloud API providers
 and local model servers like Ollama.
 
-<canvas id="quantChart" width="800" height="500" style="margin: 20px 0"></canvas>
+<canvas id="quantChart" width="800" height="600" style="margin: 20px 0"></canvas>
 <script src="https://cdn.jsdelivr.net/npm/chart.js"></script>
 <script>
 {% include quant-chart.js %}
 </script>
 
-The graph above compares 4 different versions of the Qwen 2.5 Coder 32B Instruct model,
+The graph above compares 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.
+- A [4bit quant for mlx](https://t.co/cwX3DYX35D). 
+This is the only model which was benchmarked using the "whole" [edit format](https://aider.chat/docs/more/edit-formats.html).
+The rest were benchmarked with the much more practical and challenging "diff"edit format.
 - 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, with Ollama's default 2k context window.