LLM EXPLORER 61,405 MODELS INDEXED

Nex N2.5 Mini MLX 4bit by abenzerps

By abenzerps · 1077 downloads
HF Repo ↗ Copy URL

Nex N2.5 Mini MLX 4bit is an open-source language model by abenzerps. Features: 34.7b LLM, VRAM: 19.5GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.33.

  256k-context   4-bit   4bit Base model:nex-agi/nex-n2.5-mi... Base model:quantized:nex-agi/n...   Conversational   En   Long-context   Mlx   Mlx-lm   Moe   Quantized   Qwen3 5 moe   Region:us   Safetensors   Sharded   Tensorflow   Zh
Model Card on HF 🤗: https://huggingface.co/abenzerps/Nex-N2.5-mini-MLX-4bit 

Nex N2.5 Mini MLX 4bit Parameters and Internals

LLM NameNex N2.5 Mini MLX 4bit
Repository 🤗https://huggingface.co/abenzerps/Nex-N2.5-mini-MLX-4bit 
Base Model(s)  nex-agi/Nex-N2.5-mini   nex-agi/Nex-N2.5-mini
Model Size34.7b
Required VRAM19.5 GB
Updated2026-09-16
Maintainerabenzerps
Model Typeqwen3_5_moe
Model Files  5.3 GB: 1-of-4   5.4 GB: 2-of-4   5.4 GB: 3-of-4   3.4 GB: 4-of-4
Supported Languagesen zh
Quantization Type4bit
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 4bit

Best Alternatives
Context / RAM
Downloads
Likes
Nex N2.5 Mini OptiQ 4bit0K / 22.2 GB2822
Agents A1 OptiQ 4bit0K / 22.2 GB8913
...CybersecurityLLM V1.0 Mlx 4Bit0K / 19.5 GB82047
KAT Coder V2.5 Dev OptiQ 4bit0K / 21.9 GB1143
XYZ Aquila Mini OptiQ 4bit0K / 36.3 GB343
Edge0 35B A3B Preview0K / 19.6 GB95198
Affine 5dfqbbh8ev Sft0K / 69.3 GB3880
5eqdtdzqle Ckpt1000 M70K / 71.7 GB220
Note: green Score (e.g. "73.2") means that the model is better than abenzerps/Nex-N2.5-mini-MLX-4bit.