Fine-tuned Gemma 4 MLX
Collection
4 items • Updated
Darwin-31B-Opus
Quality: quantized (8 bit, group size: 32, 8.643 bpw)
Overview
Darwin-31B-Opus is a reasoning-enhanced model created by merging google/gemma-4-31B-it (Father) and TeichAI/gemma-4-31B-it-Claude-Opus-Distill (Mother) using the Darwin V6 engine.
Darwin V6 diagnoses both parent models at the tensor level before merging, assigning an independent optimal ratio to each of the 1,188 tensors. This is fundamentally different from conventional merging tools that apply a single uniform ratio across all tensors.
Model Specifications
| Architecture | Gemma 4 Dense (Hybrid Attention: Sliding Window + Global) |
| Parameters | 31B |
| Precision | BF16 |
| Context | 256,072 |
| Languages | 140+ |
| Thinking | enable_thinking=True chain-of-thought |
| License | Apache 2.0 |
Parent Models
| Role | Model | Characteristics |
|---|---|---|
| Father | google/gemma-4-31B-it | Gemma 4 Dense 31B, multimodal, 256K context, LMArena 1452 (open model #3) |
| Mother | TeichAI/gemma-4-31B-it-Claude-Opus-Distill | Claude 4.6 Opus high-effort reasoning distillation, code/science/analysis |
Source
This model was converted to MLX format from FINAL-Bench/Darwin-31B-Opus using mlx-vlm version 0.4.4.
- Downloads last month
- 71
Model size
33B params
Tensor type
BF16
·
U32 ·
Hardware compatibility
Log In to add your hardware
8-bit
Model tree for TheCluster/Darwin-31B-Opus-MLX-8bit
Base model
google/gemma-4-31B-it Finetuned
unsloth/gemma-4-31B-it Finetuned
FINAL-Bench/Darwin-31B-Opus