LLM EXPLORER 59,420 MODELS INDEXED

Qwen1.5 1.8B Chat 4bit by mlx-community

By mlx-community · 71 downloads
HF Repo ↗ Copy URL

Qwen1.5 1.8B Chat 4bit is an open-source language model by mlx-community. Features: 1.8b LLM, VRAM: 1.5GB, Context: 32K, License: other, Quantized, LLM Explorer Score: 0.14, Arc: 38.7, HellaSwag: 60, MMLU: 45.9, GSM8K: 19.

  4bit   Chat   Conversational   En   Mlx   Quantized   Qwen2   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/mlx-community/Qwen1.5-1.8B-Chat-4bit 

Qwen1.5 1.8B Chat 4bit Parameters and Internals

Model Type 
text-generation, chat
Additional Notes 
Model was converted to MLX format.
Supported Languages 
en (Proficient)
LLM NameQwen1.5 1.8B Chat 4bit
Repository 🤗https://huggingface.co/mlx-community/Qwen1.5-1.8B-Chat-4bit 
Base Model(s)  deltawi/Qwen-1.5-1.8B-SQL   deltawi/Qwen-1.5-1.8B-SQL
Model Size1.8b
Required VRAM1.5 GB
Updated2026-07-24
Maintainermlx-community
Model Typeqwen2
Model Files  1.5 GB
Supported Languagesen
Quantization Type4bit
Model ArchitectureQwen2ForCausalLM
Licenseother
Context Length32768
Model Max Length32768
Transformers Version4.37.2
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Qwen1.5 1.8B Chat 4bit

Best Alternatives
Context / RAM
Downloads
Likes
Nano Q232K / 3.5 GB50
Palmyra Mini Thinking B128K / 3.5 GB3527
Dhanishtha128K / 3.5 GB822
LaConfiance PRYMMAL ECE TW3128K / 7.1 GB60
Reyna Mini 1.8B V0.132K / 3.7 GB662
Qwen1.5 1.8B Chat32K / 3.7 GB6668875
Qwen1.5 1.8B32K / 3.7 GB6745559
Qwen1.5 1.8B Chat Heretic32K / 3.7 GB80
Qwen1.5 1.8B Chat Heretic32K / 3.7 GB60
Colegium Ai 1.8B32K / 3.7 GB60
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Qwen1.5-1.8B-Chat-4bit.