LLM EXPLORER 60,897 MODELS INDEXED

Nex N2.5 Mini MLX 8bit by Vontra

By Vontra · 156 downloads
HF Repo ↗ Copy URL

Nex N2.5 Mini MLX 8bit is an open-source language model by Vontra. Features: 35.1b LLM, VRAM: 37.8GB, License: apache-2.0, Quantized.

  8-bit   8bit   Apple-silicon Base model:nex-agi/nex-n2.5-mi... Base model:quantized:nex-agi/n...   Conversational   Image-text-to-text   Mixture-of-experts   Mlx   Mlx-vlm   Nex-agi   Nex-n2.5   Omlx   Quantized   Qwen3 5 moe   Region:us   Safetensors   Sharded   Tensorflow   Vision   Vision-language
Model Card on HF 🤗: https://huggingface.co/Vontra/Nex-N2.5-mini-MLX-8bit 

Nex N2.5 Mini MLX 8bit Parameters and Internals

LLM NameNex N2.5 Mini MLX 8bit
Repository 🤗https://huggingface.co/Vontra/Nex-N2.5-mini-MLX-8bit 
Base Model(s)  nex-agi/Nex-N2.5-mini   nex-agi/Nex-N2.5-mini
Model Size35.1b
Required VRAM37.8 GB
Updated2026-09-12
MaintainerVontra
Model Typeqwen3_5_moe
Model Files  5.3 GB: 1-of-8   5.4 GB: 2-of-8   5.4 GB: 3-of-8   5.4 GB: 4-of-8   5.4 GB: 5-of-8   5.4 GB: 6-of-8   5.0 GB: 7-of-8   0.5 GB: 8-of-8
Quantization Type8bit
Model ArchitectureQwen3_5MoeForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version5.2.0
Tokenizer ClassTokenizersBackend
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Nex N2.5 Mini MLX 8bit

Best Alternatives
Context / RAM
Downloads
Likes
Nex N2.5 Mini MLX 6bit0K / 28.9 GB861
Nex N2.5 Mini0K / 70.4 GB3121685
Agents A10K / 70.6 GB23272629
Thomson 1.0 Small0K / 70.5 GB214109
Nex N2 Mini0K / 70.4 GB2289294
Huihui Agents A1 Abliterated0K / 70.6 GB333929
Affine 5g4yy75zuz T60K / 70.2 GB7560
Affine 5efg6cm3yl King0K / 70.3 GB5780
...yJ5ua3Sebfyr8kcVwLAdaiJLUC8pkW0K / 70.4 GB18940
Affine 5gedzafcvg Queen0K / 70.4 GB7180
Note: green Score (e.g. "73.2") means that the model is better than Vontra/Nex-N2.5-mini-MLX-8bit.