Model Intelligence Sheet
Elsephire/Qwen3.6-35B-A3B-Nex-N2-mini-80-20-Beta-GGUF overview
About this model This model was created by merging Qwen3.6 35B A3B and Nex N2 mini using Task Arithmetic with an 80/20 weighting ratio. The merge was performed…
Runs locally from ~18.97 GB disk (24 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
1 GGUF files detected
Direct downloads for local inference
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| Qwen3.6-35B-A3B-Nex-N2-mini-80-20-MTP-Beta-Q4_K_S.gguf | GGUF | Q4_K_S | 18.97 GB | Download |
Model Details
| Model ID | Elsephire/Qwen3.6-35B-A3B-Nex-N2-mini-80-20-Beta-GGUF |
|---|---|
| Author | Elsephire |
| Pipeline | image-text-to-text |
| License | mit |
| Base model | Qwen/Qwen3.6-35B-A3B,nex-agi/Nex-N2-mini |
| Last modified | 2026-07-09T13:29:06.000Z |
Model README
---
license: mit
base_model:
- Qwen/Qwen3.6-35B-A3B
- nex-agi/Nex-N2-mini
library_name: transformers
tags:
- merge
- text-generation-inference
- mtp
- image-text-to-text
---
About this model
This model was created by merging Qwen3.6-35B-A3B and Nex-N2-mini using Task Arithmetic with an 80/20 weighting ratio. The merge was performed using Minerve-Fusion, a tool that will be released open-source in the near future.
⚠️ This is a beta release. Testing and feedback are highly encouraged!
Run Elsephire/Qwen3.6-35B-A3B-Nex-N2-mini-80-20-Beta-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models