--- base_model: FINAL-Bench/Darwin-36B-Opus base_model_relation: quantized tags: - gguf - llama.cpp - imatrix - moe - reasoning - qwen3 - opal pipeline_tag: text-generation ---
This repo contains OPAL Quants of FINAL-Bench/Darwin-36B-Opus
| Tier Name | Target Size | Middle Layer Strategy |
|---|---|---|
π quality | ~23 GB | IQ4_XS |
βοΈ balanced | ~25 GB | Q5_K |
π¦ compact | ~18 GB | Q3_K |
π mini | ~14 GB | IQ2_S |
π¬ micro | ~11 GB | IQ1_M |
π€ nano | ~12 GB | IQ2_XXS |
π‘οΈ exp-minimalist | ~16 GB | IQ2_XXS (Protected Edges) |
π APEX Quantization Method
Ettore Di Giacinto & Richard Palethorpe (LocalAI Team). OPAL adapts the layer-wise precision gradients and MoE-aware tensor classification outlined in the APEX technical paper.
π Bartowski and Lamim
For the excellent semantic imatrix calibration dataset that powers OPAL's activation scaling.
π llama.cpp
Georgi Gerganov and contributors for the foundational inference and quantization engine.
π HuggingFace Accelerate
For the init_empty_weights() context manager that makes the 0-RAM "Ghost Model" possible.
π Jackrong
For the sexy markdown readme inspo.
A coffee in Ethereum would be cool! Although I don't drink coffeeβI think it tastes like burnt waterβbut a pink lemonade would be fire! π₯
0xDEE7fa8C421BD038D32e4441ea1aDe72fE973706