LLM EXPLORER 58,873 MODELS INDEXED

Qwen3 4bit Math by wesjos

By wesjos · 32 downloads
HF Repo ↗ Copy URL

Qwen3 4bit Math is an open-source language model by wesjos. Features: 4b LLM, VRAM: 8.1GB, Context: 40K, License: apache-2.0, Quantized, LLM Explorer Score: 0.19.

  4bit   Autotrain compatible Base model:finetune:unsloth/qw...   Base model:unsloth/qwen3-4b   Conversational   Dataset:mlabonne/finetome-100k Dataset:unsloth/openmathreason...   En   Endpoints compatible   Math   Quantized   Qwen3   Region:us   Safetensors   Sharded   Tensorflow   Unsloth   Zh
Model Card on HF 🤗: https://huggingface.co/wesjos/Qwen3-4bit-math 

Qwen3 4bit Math Parameters and Internals

LLM NameQwen3 4bit Math
Repository 🤗https://huggingface.co/wesjos/Qwen3-4bit-math 
Base Model(s)  Qwen3 4bit Math   Qwen3 4B   wesjos/Qwen3-4bit-math   unsloth/Qwen3-4B
Model Size4b
Required VRAM8.1 GB
Updated2025-07-28
Maintainerwesjos
Model Typeqwen3
Model Files  5.0 GB: 1-of-2   3.1 GB: 2-of-2
Supported Languagesen
Quantization Type4bit
Model ArchitectureQwen3ForCausalLM
Licenseapache-2.0
Context Length40960
Model Max Length40960
Transformers Version4.53.2
Tokenizer ClassQwen2Tokenizer
Padding Token<|vision_pad|>
Vocabulary Size151936
Torch Data Typefloat16
Errorsreplace

Best Alternatives to Qwen3 4bit Math

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3 4b Merged Txt256K / 8.1 GB5350
...Instruct 2507 Unsloth Bnb 4bit256K / 3.5 GB10812917
Mini Coder 4B OptiQ 4bit256K / 3 GB3101
Qwen3.8 4B Distilled256K / 8.1 GB900
FastContext 1.0 4B SFT 8bit256K / 4.3 GB1201
...wen3 4B Thinking 2507 MLX 4bit256K / 2.3 GB5322514
...wen3 4B Thinking 2507 MLX 8bit256K / 4.3 GB447318
Qwen3 4B Instruct 2507 4bit256K / 2.3 GB4095511
...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 wesjos/Qwen3-4bit-math.