Darwin-27B-Opus
Quality: quantized (mixed quants per tensor, group size: 32, 9.450 bpw)
Most layers use 8-bit affine quantization with a group size 32, embeddings and some other layers are saved in bf16.
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) |
| Languages | 201 |
| Thinking Mode | Enabled |
Parent Models
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 using mlx-vlm version
0.4.4.
