Planium-2B
Planium-2B is a 2B fine-tune of Qwen3.5 specialized in automated planning and its standard notation, PDDL (Planning Domain Definition Language). It is built primarily for robotics and other control systems.
In its 4-bit quantized build, it is small enough to run on an ordinary PC or an embedded board such as an NVIDIA Jetson — no cloud API, nothing leaves your machine.
What it does
Classical planning in PDDL, largely limited to the :strips and :strips :typing fragments:
- turning a plain-language request into PDDL — typically the
:goalor the problem file for a given domain, - reading and explaining an existing domain, problem or plan,
- reasoning about states, preconditions, effects and goals,
- spotting what is wrong in a piece of PDDL,
- calling tools: it is trained to work in an agentic loop and to emit tool calls, so it can drive a parser, a planner or a plan validator itself instead of only producing text.
Temporal planning, numeric fluents and the richer ADL constructs are much less well supported.
The fine-tuning also mitigates a failure mode of the base Qwen3.5 on these tasks: reasoning that never terminates, or that drags on far longer than the problem warrants without getting closer to an answer. Planium-2B keeps its reasoning short and commits to an answer.
Files
| File | Description |
|---|---|
model.safetensors-00001-of-00001.safetensors | Full weights (bfloat16) |
gguf/model.gguf | Quantized build for llama.cpp (Q4_K_M, ~1.3 GB) |
Usage
llama.cpp
Download gguf/model.gguf and point llama-cli at it:
llama-cli -m /path/to/model.gguf
Or serve it over an OpenAI-compatible API:
llama-server -m /path/to/model.gguf --port 8080
Transformers
from transformers import AutoModelForImageTextToText, AutoTokenizer
model_id = "valentin0901/Planium-2B"
tok = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForImageTextToText.from_pretrained(model_id, dtype="bfloat16", device_map="auto")
messages = [{"role": "user", "content": "Write a STRIPS blocksworld domain."}]
inputs = tok.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(model.device)
out = model.generate(inputs, max_new_tokens=1024)
print(tok.decode(out[0][inputs.shape[-1]:], skip_special_tokens=True))
Built for NeuroPlan
Planium-2B is the model behind NeuroPlan, a neuro-symbolic planning system that bridges large language models and symbolic planners: it turns a request into PDDL, hands it to the planner and runs the resulting plan.
| 3D Blocks World | Sokoban |
|---|---|
 |  |
| Drone patrol | PDDL chat |
|---|---|
 |  |
License
MIT — see LICENSE.
Status
Planium-2B is a work in progress. It can make mistakes.