Darwin-35B-A3B-Opus
Quality: quantized (mixed quants per tensor, group size: 32, 9.191 bpw)
Most layers use 8-bit affine quantization with a group size 32, embeddings and some other layers are saved in bf16.
Model Specifications
| Architecture | Qwen3.5 MoE (Gated DeltaNet + MoE) |
| Total Parameters | 35B |
| Active Parameters | 3B per forward pass |
| Layers | 40 |
| Layout | 10 x (3 x GDN-MoE + 1 x Attention-MoE) |
| Experts | 256 (8 routed + 1 shared active) |
| Context Length | 262,144 native |
| Languages | 201 |
| Multimodal | Image and Video |
| License | Apache 2.0 |
Parent Models
Both parents share the identical Qwen3.5-35B-A3B architecture (40 layers, 256 experts, GDN+MoE hybrid). The Mother is a LoRA SFT on the same base — not a different architecture. "Text-only" refers to the training data (Claude 4.6 Opus reasoning chains), not the model structure.
| Role | Model | Architecture | Training |
|---|---|---|---|
| Father | Qwen/Qwen3.5-35B-A3B | Qwen3.5-35B-A3B | Original pre-training + RLHF |
| Mother | Jackrong/Qwen3.5-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled | Qwen3.5-35B-A3B (same) | LoRA SFT with text-only Claude reasoning chains |
Source
This model was converted to MLX format from FINAL-Bench/Darwin-35B-A3B-Opus using mlx-vlm version 0.4.4.