Maris3D-Blender 0.2

A 0.5B model that plans Blender scenes in words. Code builds them.

You describe a scene in a sentence. The model answers in plain words: which things, how many, what they are made of and where they stand. The Maris3D app turns those words into exact Blender tool calls, builds the scene, reads it back and checks it. The model never writes a number; code computes every size and position.

It runs fully offline on your own machine: one 531 MB base file plus a 12 MB adapter.

GitHub Release License: Apache-2.0 Blender 4.2+

Install in one command

No need to clone anything. This installs the Blender add-on, downloads the two model files below (sha256-checked) and tests them in your Blender. Needs Python 3.9+ and Blender 4.2+.

macOS / Linux Windows (PowerShell)
curl -fsSL https://raw.githubusercontent.com/slm4apps/maris3d/main/install.sh | sh powershell -ExecutionPolicy ByPass -c "irm https://raw.githubusercontent.com/slm4apps/maris3d/main/install.ps1 | iex"

Then: maris3d serve start, open Blender, press N in the 3D View, pick the Maris3D Copilot tab, type a sentence and press Run. Try:

Build one thing Build a whole scene Change what is there
a small house a park with a bench, a tree behind the bench and a lamp next to the bench Make the bench blue. then Move the lamp to the left of the bench.

What is new in 0.2

  • Words, not numbers. 0.1 wrote tool calls with coordinates. 0.2 answers in one small word language (things, relations such as behind or on top of, sizes such as half or double), and the app's compiler writes the tool calls.
  • One adapter for everything: planning, designing a new thing's parts, word edits and talk, instead of 0.1's separate edit and planner adapters.
  • Animation by the app's code: "a ball bouncing twice", "a moon going round a planet".
  • Edits by words. "Make the table darker", "move the lamp next to the sofa": the model says what changes, code applies it and checks it.
  • Talk. Ask about the scene and it answers from what is there.
  • Breaking change: 0.2 needs the 0.2 app. 0.1 stays available as Maris3D-Blender v0.1.0 and at tag v0.1.1 on GitHub.

Files

File What it is
maris3d-slm-blender-0.5b-q8_0.gguf The base (531 MB), the same file as 0.1.
maris3d-slm-blender-0.5b-v0.2.0-lora-f16.gguf The adapter (12 MB): plans, parts, word edits, talk.
Modelfile The Ollama entry maris3d-slm-blender-0.5b, with the settings the app sends.
MANIFEST.json, SHA256SUMS The current file of each role with its sha256, read by maris3d update.

Measured

Held-out sets the model never trained on, scored by outcome through the app's own code.

What Result
Plan from one sentence: the things named are right 97.3 % (3,033 things in 716 held-out sentences)
the relation (behind, next to, on top of ...) is right 97.0 %
the thing it is placed by is right 95.8 %
Parts of a new thing: the answer parses 99.9 % (1,268 held-out names)
the design passes the app's rules 95.7 %
Word edits: the change asked for is the change made 90.4 % (726 held-out change requests)
Talk: the reply is right 95.8 % (118 held-out talk turns)
Talk: things invented that are not in the scene 0 in 383 turns
The 0.1 demo scene, its 204 requests replayed through the 0.2 app: built exactly (right thing, place and size) 92.2 % (188 of 204)

Ways to run it

  • The Maris3D app (recommended). maris3d install fetches the base and the adapter; maris3d serve start runs llama-server with them. maris3d update fetches a newer adapter later without fetching the base again.
  • llama-server by hand: llama-server -m maris3d-slm-blender-0.5b-q8_0.gguf --lora maris3d-slm-blender-0.5b-v0.2.0-lora-f16.gguf --lora-init-without-apply --jinja -c 8192
  • Ollama: ollama create maris3d-slm-blender-0.5b -f Modelfile (that is :latest, the name the app uses; ollama cp maris3d-slm-blender-0.5b maris3d-slm-blender-0.5b:0.2.0 keeps this version by name), then pick Ollama in the app's settings.

Serve with temperature 0, a context of 8,192 and repeat penalty 1.05 (the app sends these on every request).

Speed

Base + adapter in llama-server, as the app serves it, on CPU only:

ran on generation prompt reading memory
4-core Intel laptop CPU (i7-6700HQ), 4 threads 28.5 tok/s 142 tok/s 876 MB

Measured with a 555-token prompt and 128 generated tokens, three runs (28.2 to 28.8 tok/s).

Scope

0.2 builds, edits and talks about scenes made of things: furniture, buildings, vehicles, people, plants, street and room scenes. It animates them with a set of motions the app's code writes (spin, bounce, move, rise, grow, shrink, swing, orbit, pulse, colour change). Lights, cameras and text are not in 0.2; for those the model says it cannot.

Training

Base: Qwen2.5-Coder-0.5B-Instruct (Apache-2.0). The adapter is a LoRA trained on text-only conversations in the word language.

Licence

Apache-2.0 for the weights and code (see LICENSE and NOTICE). The Blender add-on, which runs inside Blender, is GPL-3.0-or-later. Base model Qwen2.5-Coder-0.5B-Instruct is Apache-2.0 (Alibaba Qwen team). This project is not affiliated with, endorsed by, or supported by the Blender Foundation. "Blender" is a trademark of the Blender Foundation.

Downloads last month
1,124
GGUF
Model size
0.5B params
Architecture
qwen2
Hardware compatibility
Log In to add your hardware

8-bit

16-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for slm4apps/Maris3D-Blender

Finetuned
(119)
this model

Collection including slm4apps/Maris3D-Blender