LLM EXPLORER 61,249 MODELS INDEXED

Nex N2.5 Mini W4A16 AutoRound by quant-mind

By quant-mind · 230 downloads
HF Repo ↗ Copy URL

Nex N2.5 Mini W4A16 AutoRound is an open-source language model by quant-mind. Features: 6b LLM, VRAM: 18.9GB, License: apache-2.0, LLM Explorer Score: 0.31.

  4-bit   Agentic   Auto-round Base model:nex-agi/nex-n2.5-mi... Base model:quantized:nex-agi/n...   Conversational   Gptq   Image-text-to-text   Int4   Intel   Marlin   Qwen3 5 moe   Region:us   Safetensors   Sglang   Sharded   Tensorflow   Vllm   W4a16
Model Card on HF 🤗: https://huggingface.co/quant-mind/Nex-N2.5-mini-W4A16-AutoRound 

Nex N2.5 Mini W4A16 AutoRound Parameters and Internals

LLM NameNex N2.5 Mini W4A16 AutoRound
Repository 🤗https://huggingface.co/quant-mind/Nex-N2.5-mini-W4A16-AutoRound 
Base Model(s)  nex-agi/Nex-N2.5-mini   nex-agi/Nex-N2.5-mini
Model Size6b
Required VRAM18.9 GB
Updated2026-09-15
Maintainerquant-mind
Model Typeqwen3_5_moe
Model Files  0.4 GB: 1-of-41   0.4 GB: 2-of-41   0.4 GB: 3-of-41   0.4 GB: 4-of-41   0.4 GB: 5-of-41   0.4 GB: 6-of-41   0.4 GB: 7-of-41   0.4 GB: 8-of-41   0.4 GB: 9-of-41   0.4 GB: 10-of-41   0.4 GB: 11-of-41   0.4 GB: 12-of-41   0.4 GB: 13-of-41   0.4 GB: 14-of-41   0.4 GB: 15-of-41   0.4 GB: 16-of-41   0.4 GB: 17-of-41   0.4 GB: 18-of-41   0.4 GB: 19-of-41   0.4 GB: 20-of-41   0.4 GB: 21-of-41   0.4 GB: 22-of-41   0.4 GB: 23-of-41   0.4 GB: 24-of-41   0.4 GB: 25-of-41   0.4 GB: 26-of-41   0.4 GB: 27-of-41   0.4 GB: 28-of-41   0.4 GB: 29-of-41   0.4 GB: 30-of-41   0.4 GB: 31-of-41   0.4 GB: 32-of-41   0.4 GB: 33-of-41   0.4 GB: 34-of-41   0.4 GB: 35-of-41   0.4 GB: 36-of-41   0.4 GB: 37-of-41   0.4 GB: 38-of-41   0.4 GB: 39-of-41   0.4 GB: 40-of-41   2.9 GB: 41-of-41
Model ArchitectureQwen3_5MoeForConditionalGeneration
Licenseapache-2.0
Transformers Version5.17.0
Torch Data Typefloat16