LLM EXPLORER 62,007 MODELS INDEXED

Qwen3.8 2B MLX 4.83B by dalatexcoder

By dalatexcoder · 281 downloads
HF Repo ↗ Copy URL

Qwen3.8 2B MLX 4.83B is an open-source language model by dalatexcoder. Features: 2b LLM, VRAM: 1.3GB, License: apache-2.0, LLM Explorer Score: 0.31.

  4-bit Base model:empero-ai/qwen3.8-2... Base model:quantized:empero-ai...   Conversational   Distillation   Edge   Empero-ai   En   Function-calling   Mlx   Qwen3.5   Qwen3.8   Qwen3 5   Reasoning   Region:us   Safetensors   Sft
Model Card on HF 🤗: https://huggingface.co/dalatexcoder/Qwen3.8-2B-MLX-4.83B 

Qwen3.8 2B MLX 4.83B Parameters and Internals

LLM NameQwen3.8 2B MLX 4.83B
Repository 🤗https://huggingface.co/dalatexcoder/Qwen3.8-2B-MLX-4.83B 
Base Model(s)  empero-ai/Qwen3.8-2B-Distill   empero-ai/Qwen3.8-2B-Distill
Model Size2b
Required VRAM1.3 GB
Updated2026-09-23
Maintainerdalatexcoder
Model Typeqwen3_5
Model Files  1.3 GB
Supported Languagesen
Model ArchitectureQwen3_5ForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version4.57.0.dev0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Qwen3.8 2B MLX 4.83B

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3.5 2B0K / 4.5 GB2633311352
WeMM Embedding 2B0K / 5.4 GB543368
Qwen3.5 2B Base0K / 4.5 GB80959182
Qwen3.8 2B Distill0K / 4.5 GB205624
Qwen3.5 2B0K / 4.5 GB10348718
Decider 2B Vision0K / 4.4 GB1055
Tamil Lm 2B Instruct0K / 0.8 GB2077
Qwen3.5 2B Manumit V20K / 4.4 GB4310
Qwen3.5 2B Vi SFT0K / 4.5 GB1911
Qwen3.8 2B0K / 4.5 GB31913
Note: green Score (e.g. "73.2") means that the model is better than dalatexcoder/Qwen3.8-2B-MLX-4.83B.