LLM EXPLORER 61,135 MODELS INDEXED

Qwen3.6 23B A3B Niwaki V2.1 4bit Mlx by neopolita

By neopolita · 19 downloads
HF Repo ↗ Copy URL

Qwen3.6 23B A3B Niwaki V2.1 4bit Mlx is an open-source language model by neopolita. Features: 35b LLM, VRAM: 14GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.27.

  8-bit   8bit Base model:mlx-community/qwen3... Base model:quantized:mlx-commu...   Conversational   Mixture-of-experts   Mlx   Moe   Pruning   Quantization   Quantized   Qwen3 5 moe   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/neopolita/Qwen3.6-23B-A3B-Niwaki-v2.1-4bit-mlx 

Qwen3.6 23B A3B Niwaki V2.1 4bit Mlx Parameters and Internals

LLM NameQwen3.6 23B A3B Niwaki V2.1 4bit Mlx
Repository 🤗https://huggingface.co/neopolita/Qwen3.6-23B-A3B-Niwaki-v2.1-4bit-mlx 
Base Model(s)  mlx-community/Qwen3.6-35B-A3B-8bit   mlx-community/Qwen3.6-35B-A3B-8bit
Model Size35b
Required VRAM14 GB
Updated2026-09-14
Maintainerneopolita
Model Typeqwen3_5_moe
Model Files  5.4 GB: 1-of-3   5.3 GB: 2-of-3   3.3 GB: 3-of-3
Quantization Type8bit
Model ArchitectureQwen3_5MoeForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version4.57.1
Tokenizer ClassTokenizersBackend
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Qwen3.6 23B A3B Niwaki V2.1 4bit Mlx

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3.6 35B A3B MLX 4bit0K / 20.5 GB5131936
Qwen3.6 35B A3B MLX 6bit0K / 28.9 GB4785922
Qwen3.6 35B A3B MLX 8bit0K / 37.8 GB4735371
Qwen3.6 35B A3B UD MLX 4bit0K / 21.6 GB15720112
Qwen3.6 35B A3B OQ4e Fp16 Mtp0K / 22.4 GB1871
Qwen3.6 35B A3B MLX 8bit0K / 37.8 GB386241
Qwen3.6 35B A3B 2Bit GSQ0K / 13.5 GB21197
Qwen3.6 35B A3B 6bit0K / 28.9 GB27428
Qwen3.6 35B A3B UD MLX 3bit0K / 17.3 GB229213
Nail Qwen3.6 35B A3B MLX 5bit0K / 27.5 GB831
Note: green Score (e.g. "73.2") means that the model is better than neopolita/Qwen3.6-23B-A3B-Niwaki-v2.1-4bit-mlx.