---
license: apache-2.0
base_model:
- Qwen/Qwen3.6-27B
datasets:
- ProCreations/grug-think
- ProCreations/grug-think-v3-10k
pipeline_tag: text-generation
---
## 1. Introduction
We're introducing **LRM-3.2**, a reasoning model built around a single idea: thinking should be *fast, direct, and dense* — not padded. LRM-3.2 keeps the full depth of chain-of-thought reasoning while stripping out the narrative scaffolding that most models use to fill space.
Same reasoning. Same depth. Way fewer tokens. LRM-3.2 throws the grammar padding in the fire and keeps all the brain meat. The final answer still comes out in normal, full-quality English — the compressed voice lives only inside the thinking process.
## 2. Key Capabilities
- **Adaptive Depth:** Thinking length scales with task difficulty, not with habit. Easy problems get a one-line think; hard problems still get full, structured deliberation.
- **Unchanged Output Quality:** Compression happens exclusively in the reasoning trace. Final answers remain complete, natural, and equivalent in quality to verbose-thinking models.
- **Fast, Direct Inference:** Dramatically shorter think blocks translate directly into lower latency and lower token spend per response, without a distillation-style drop in capability.
- **Reliable Under Long Sessions:** Reasoning stays dense and on-task across extended agentic and multi-step work, rather than drifting into repetitive verbal habits.
## 3. Performance
| |
LRM-3.2 |
Qwen3.6-27B |
| Reasoning & Coding |
| GSM8K |
95.8 |
— |
| HumanEval |
86.9 |
— |
*"—" indicates a score not yet measured on this harness. Both benchmarks reflect matched-quality answers between LRM-3.2 and its base model — the difference lives in the think trace, not the final result.*
## 4. Efficiency in Practice
Same problem, same correct solution, radically different think length.
Task: write `separate_paren_groups`, a function that splits a string of parentheses into its top-level balanced groups.
**Qwen3.6-27B think: 6,539 tokens.** Starts like this and keeps going for pages:
The user wants a Python function separate_paren_groups that takes a string of parentheses and spaces, and returns a list of strings. Each string in the list should represent a balanced group of parentheses that is not nested within another group. Spaces should be ignored...
**LRM-3.2 think: 33 tokens. The whole thing:**
Strip spaces. Scan chars; depth counts open parens. When depth becomes 0 after a close, current group finished; append and reset. Empty input -> [].
Same answer quality. 198x less think.
## 5. Training
LRM-3.2 is fine-tuned from **Qwen3.6-27B** on the [grug-think](https://huggingface.co/datasets/ProCreations/grug-think) and [grug-think-v3-10k](https://huggingface.co/datasets/ProCreations/grug-think-v3-10k) datasets, applying a think-only loss on trajectory data so the compressed reasoning style is learned without touching final-answer quality.
LRM-3.2 is directly inspired by [ProCreations/grug-27b](https://huggingface.co/ProCreations/grug-27b), which pioneered this padding-free thinking approach on the same base model family. LRM-3.2 adapts that approach under the OrionLLM naming and evaluation pipeline.
## 6. Architecture
LRM-3.2 is built on **Qwen3.6-27B**, a 27B-parameter dense model, fine-tuned to compress the reasoning trace while leaving final-answer generation untouched. No changes are made to the base tokenizer, context length, or output formatting — only the internal thinking style is altered.
---
**Orion Research - 2026**