Modelpublic

TheCluster/Darwin-27B-Opus-MLX-mxfp4

sourceHugging Faceapache-2.0updated 6mo agoView on Hugging Face

0likes5downloads

Model Card

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	Foundation architecture, native reasoning, 201-language support
Mother (Knowledge)	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: hiddensize=4096, intermediatesize=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.