---
license: apache-2.0
base_model:
- FINAL-Bench/Darwin-27B-Opus
pipeline_tag: image-text-to-text
library_name: mlx
language:
- en
- zh
- ru
- es
- fr
- it
- ja
- ko
- af
- de
- ar
- tr
- is
- pl
- sw
- sv
- nl
- he
- id
- uk
- fa
- pa
- pt
- ms
- fi
- el
tags:
- mxfp4
- mixed-precision
---
# Darwin-27B-Opus

**Quality**: quantized (***mxfp4**, 4.449 bpw*)

**Darwin-27B-Opus** is a 27-billion-parameter language model produced entirely through evolutionary crossbreeding of pretrained models, requiring zero additional training, zero data, and a single GPU. On the GPQA Diamond benchmark — a graduate-level scientific reasoning evaluation comprising 198 expert-crafted questions in physics, chemistry, and biology — Darwin-27B-Opus achieves 86.9%, surpassing its progenitor Qwen3.5-27B (85.5%) by +1.4 percentage points and securing 5th place on the HuggingFace GPQA leaderboard.

### Model Specifications
| | |
|---|---|
| Architecture | Qwen3.5 Dense (GatedDeltaNet) |
| Parameters | 27B |
| Hidden Size | 4096 |
| Intermediate Size | 17408 |
| Layers | 64 |
| Context Length | 262,144 (extensible to 1M via YaRN) |
| Precision | BF16 |
| Languages | 201 |
| Thinking Mode | Enabled |

### Parent Models

| Role | Model | Contribution |
|---|---|---|
| **Father (Structure)** | [Qwen/Qwen3.5-27B](https://huggingface.co/Qwen/Qwen3.5-27B) | Foundation architecture, native reasoning, 201-language support |
| **Mother (Knowledge)** | [Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled](https://huggingface.co/Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled) | Claude 4.6 Opus structured reasoning patterns via SFT distillation |

Both parents share identical architecture: hidden_size=4096, intermediate_size=17408, 64 layers — ensuring **100% structural compatibility** for FFN crossbreeding.

-----
### Source
This model was converted to MLX format from [`FINAL-Bench/Darwin-27B-Opus`](https://huggingface.co/FINAL-Bench/Darwin-27B-Opus) using mlx-vlm version **0.4.4**.