JackBinary
/

Qwen3.5-24B-A3B-Claude-Opus-Gemini-3.1-Pro-Reasoning-Distilled

Text Generation

qwen3_5_moe_text

text-generation-inference

Model card Files Files and versions

Qwen3.5-24B-A3B — Claude Opus + Gemini 3.1 Pro Reasoning Distill

A fine-tuned version of sandeshrajx/Qwen3.5-24B-A3B-REAP-0.32, itself based on Qwen3.5-35B-A3B. The goal of this project is simple: the best reasoning model that can comfortably fit and run on a 16GB GPU.

Inspired By

Jackrong's distills

Uploaded model

Developed by: JackBinary
License: apache-2.0
Finetuned from model : sandeshrajx/Qwen3.5-24B-A3B-REAP-0.32

This qwen3_5_moe_text model was trained 2x faster with Unsloth

Downloads last month: 92

Safetensors

Model size

24B params

Tensor type

F16

·

Model tree for JackBinary/Qwen3.5-24B-A3B-Claude-Opus-Gemini-3.1-Pro-Reasoning-Distilled

Base model

sandeshrajx/Qwen3.5-24B-A3B-REAP-0.32

Finetuned

(2)

this model

Datasets used to train JackBinary/Qwen3.5-24B-A3B-Claude-Opus-Gemini-3.1-Pro-Reasoning-Distilled

Collection including JackBinary/Qwen3.5-24B-A3B-Claude-Opus-Gemini-3.1-Pro-Reasoning-Distilled

Model Mad Science

Experimental models with weird architectures. Frankenmerges, layer duplications, expert pruning, expert merging, and whatever else seems worth trying. • 4 items • Updated Mar 17