LLM EXPLORER 64,206 MODELS INDEXED

Qwen3 4B Base Mlx 4Bit by johnlakness

By johnlakness · 73 downloads
HF Repo ↗ Copy URL

Qwen3 4B Base Mlx 4Bit is an open-source language model by johnlakness. Features: 4b LLM, VRAM: 2.3GB, Context: 32K, License: apache-2.0, Quantized, LLM Explorer Score: 0.19.

  4-bit   4bit Base model:quantized:qwen/qwen...   Base model:qwen/qwen3-4b-base   Conversational   Endpoints compatible   Mlx   Quantized   Qwen3   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/johnlakness/Qwen3-4B-Base-mlx-4Bit 

Qwen3 4B Base Mlx 4Bit Parameters and Internals

LLM NameQwen3 4B Base Mlx 4Bit
Repository 🤗https://huggingface.co/johnlakness/Qwen3-4B-Base-mlx-4Bit 
Base Model(s)  Qwen3 4B Base   Qwen/Qwen3-4B-Base
Model Size4b
Required VRAM2.3 GB
Updated2026-10-14
Maintainerjohnlakness
Model Typeqwen3
Model Files  2.3 GB
Quantization Type4bit
Model ArchitectureQwen3ForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.51.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Qwen3 4B Base Mlx 4Bit

Best Alternatives
Context / RAM
Downloads
Likes
...Instruct 2507 Unsloth Bnb 4bit256K / 3.5 GB10597517
Qwen3 4b Merged Txt256K / 8.1 GB5350
...wen3 4B Thinking 2507 MLX 4bit256K / 2.3 GB5322514
Mini Coder 4B OptiQ 4bit256K / 3 GB3101
...wen3 4B Thinking 2507 MLX 8bit256K / 4.3 GB447318
Qwen3 4B Instruct 2507 4bit256K / 2.3 GB4095511
Qwen3.8 4B Distilled256K / 8.1 GB900
FastContext 1.0 4B SFT 8bit256K / 4.3 GB1201
...wen 3 4b Mythos Finetune 16bit256K / 8.1 GB920
EduMentor Qwen3 4B FP16256K / 8.1 GB751
Note: green Score (e.g. "73.2") means that the model is better than johnlakness/Qwen3-4B-Base-mlx-4Bit.