LLM EXPLORER 66,704 MODELS INDEXED

Myth 4B by dracko14

By dracko14 · 53 downloads
HF Repo ↗ Copy URL

Myth 4B is an open-source language model by dracko14. Features: 4b LLM, VRAM: 9.3GB, License: mit, Quantized.

Base model:jackrong/qwen3.5-4b... Base model:merge:jackrong/qwen... Base model:merge:qwen/qwen3.5-...   Base model:qwen/qwen3.5-4b   Coding   Conversational   En   Endpoints compatible   Gguf   Image-text-to-text   Math   Merge   Multilingual   Myth   Q4   Quantized   Qwen3.5   Qwen3 5   Reasoning   Region:us   Safetensors   Sharded   Slerp   Tensorflow
Model Card on HF 🤗: https://huggingface.co/dracko14/Myth-4B 

Myth 4B Parameters and Internals

LLM NameMyth 4B
Repository 🤗https://huggingface.co/dracko14/Myth-4B 
Base Model(s)  Qwen/Qwen3.5-4B   Jackrong/Qwen3.5-4B-Neo   Qwen/Qwen3.5-4B   Jackrong/Qwen3.5-4B-Neo
Model Size4b
Required VRAM9.3 GB
Updated2026-11-05
Maintainerdracko14
Model Typeqwen3_5
Model Files  2.8 GB   5.6 GB: 1-of-8   0.7 GB: 2-of-8   0.9 GB: 3-of-8   1.1 GB: 4-of-8   0.4 GB: 5-of-8   0.2 GB: 6-of-8   0.2 GB: 7-of-8   0.2 GB: 8-of-8
Supported Languagesen
GGUF QuantizationYes
Quantization Typeq4|gguf|q4_k
Model ArchitectureQwen3_5ForConditionalGeneration
Licensemit
Model Max Length262144
Transformers Version4.57.0.dev0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Myth 4B

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3.5 4B 3D Coder0K / 9.1 GB44825465
Qwen3.5 4B Heretic0K / 9.1 GB389324
... Opus Reasoning Distilled GGUF0K / 0.7 GB338962154
Qwen3.5 4B Amadeus0K / 9.1 GB8113
Rudra0K / 9.3 GB5361
Baphomet 1.0 4B0K / 9.5 GB3333
Dahono 4B0K / 9.3 GB6553
Cowboy0K / 0.7 GB6461
Cowboy0K / 0.7 GB5291
Shakespeare0K / 0.7 GB4811
Note: green Score (e.g. "73.2") means that the model is better than dracko14/Myth-4B.