A fine-tune of
Qwen2.5-Coder-7B-Instruct
that turns natural-language part
descriptions into executable
CadQuery
(Python) scripts producing valid,
dimensionally-correct B-rep solids exportable to STEP/STL.
Trained with LoRA (rank 16, 16 layers) via
mlx-lm
on an Apple M4 Max; this
repo contains the
fused 4-bit MLX weights
. A GGUF build for
llama.cpp/Ollama is published alongside this repo.
Prompt contract
Use this exact system prompt (the model was trained with it):
You are a CAD design assistant. Given a description of a mechanical part,
respond with a complete CadQuery (Python) script that builds it. Use
millimeters. The script must import cadquery as cq and assign the final
single-solid model to a variable named
result
. Respond with only the code.
Set the stop token to
<|im_end|>
.
mlx_lm.generate --model yuvit-batra/qwen2.5-coder-7b-cadquery-mlx-4bit \
--prompt "Design a 60mm diameter flange, 10mm thick, with a 20mm bore and six 6mm bolt holes on a 44mm circle." \
--max-tokens 1024 --temp 0.2
8,468 synthetic
samples across 22 parametric part families (plates,
brackets, flanges, gears, shafts, enclosures, turned/chess-piece-like parts,
phone stands, trays, hooks, clips, ISO fasteners...). Every sample was
executed in a sandbox and verified to produce a valid single solid with a
bounding box matching its description.
4,000 real-world
human-designed models: DeepCAD construction sequences
with
Text2CAD
annotations (CC-BY-NC-SA-4.0), converted to CadQuery and re-validated.
9
permissively-licensed GitHub CadQuery examples.
Evaluation (geometric, not textual)
Generated code is executed; solids are checked for validity and dimensional
accuracy vs reference geometry (sorted-bbox within 10%/axis, volume within 15%).
Metric (n=25 test / n=33 novel)
Base Qwen2.5-Coder-7B
This model
Test: executes
28%
80%
Test: valid single solid
24%
80%
Test: bbox accuracy
33%
45%
Novel prompts: executes
64%
73%
Novel prompts: valid solid
48%
67%
The novel-prompt set includes chess pieces, phone docks, organizers, and other
consumer parts phrased unlike the training templates.
Limitations & license
Trained for
single-part
generation (no assemblies) in millimeters.
~32% of training data (the Text2CAD portion) uses normalized coordinates
("units"); prompts phrased in mm behave best.
Dataset lineage includes CC-BY-NC-SA-4.0 data (Text2CAD annotations), so
this model is released under
CC-BY-NC-SA-4.0 — non-commercial use only
.
Validate generated geometry before manufacturing; the model can produce
dimensionally plausible but incorrect parts.
Runs of yuvit-batra qwen2.5-coder-7b-cadquery-gguf on huggingface.co
1.1K
Total runs
17
24-hour runs
38
3-day runs
88
7-day runs
795
30-day runs
More Information About qwen2.5-coder-7b-cadquery-gguf huggingface.co Model
More qwen2.5-coder-7b-cadquery-gguf license Visit here:
qwen2.5-coder-7b-cadquery-gguf huggingface.co is an AI model on huggingface.co that provides qwen2.5-coder-7b-cadquery-gguf's model effect (), which can be used instantly with this yuvit-batra qwen2.5-coder-7b-cadquery-gguf model. huggingface.co supports a free trial of the qwen2.5-coder-7b-cadquery-gguf model, and also provides paid use of the qwen2.5-coder-7b-cadquery-gguf. Support call qwen2.5-coder-7b-cadquery-gguf model through api, including Node.js, Python, http.
qwen2.5-coder-7b-cadquery-gguf huggingface.co is an online trial and call api platform, which integrates qwen2.5-coder-7b-cadquery-gguf's modeling effects, including api services, and provides a free online trial of qwen2.5-coder-7b-cadquery-gguf, you can try qwen2.5-coder-7b-cadquery-gguf online for free by clicking the link below.
yuvit-batra qwen2.5-coder-7b-cadquery-gguf online free url in huggingface.co:
qwen2.5-coder-7b-cadquery-gguf is an open source model from GitHub that offers a free installation service, and any user can find qwen2.5-coder-7b-cadquery-gguf on GitHub to install. At the same time, huggingface.co provides the effect of qwen2.5-coder-7b-cadquery-gguf install, users can directly use qwen2.5-coder-7b-cadquery-gguf installed effect in huggingface.co for debugging and trial. It also supports api for free installation.
qwen2.5-coder-7b-cadquery-gguf install url in huggingface.co:
