LLM EXPLORER 59,516 MODELS INDEXED

Ymail Search Qwen2 0.5B 16bit by kevin36524

By kevin36524 · 16 downloads
HF Repo ↗ Copy URL

Ymail Search Qwen2 0.5B 16bit is an open-source language model by kevin36524. Features: 0.5b LLM, VRAM: 1GB, Context: 128K, License: apache-2.0, Quantized, LLM Explorer Score: 0.13.

  4bit   Conversational   En   Endpoints compatible   Pytorch   Quantized   Qwen2   Region:us   Sft   Trl   Unsloth
Model Card on HF 🤗: https://huggingface.co/kevin36524/ymail_search_qwen2-0.5B-16bit 

Ymail Search Qwen2 0.5B 16bit Parameters and Internals

Model Type 
text-generation-inference, transformers, unsloth, qwen2, trl, sft
Additional Notes 
This Qwen2 model was trained 2x faster with Unsloth and Huggingface's TRL library.
LLM NameYmail Search Qwen2 0.5B 16bit
Repository 🤗https://huggingface.co/kevin36524/ymail_search_qwen2-0.5B-16bit 
Base Model(s)  unsloth/Qwen2-0.5b-bnb-4bit   unsloth/Qwen2-0.5b-bnb-4bit
Model Size0.5b
Required VRAM1 GB
Updated2026-08-07
Maintainerkevin36524
Model Typeqwen2
Model Files  1.0 GB
Supported Languagesen
Quantization Type4bit
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length131072
Model Max Length131072
Transformers Version4.41.2
Tokenizer ClassQwen2Tokenizer
Padding Token<|PAD_TOKEN|>
Vocabulary Size151936
Torch Data Typefloat16
Errorsreplace

Best Alternatives to Ymail Search Qwen2 0.5B 16bit

Best Alternatives
Context / RAM
Downloads
Likes
Qwen2 0.5B Finetune Exp 2128K / 1 GB160
Qwen2 0.5B 20240829 175401128K / 1 GB80
Qwen2 0.5B Bnb 4bit128K / 0.5 GB11233
Qwen2 0.5B Alpaca Merged St128K / 1 GB60
Qwen2 0.5B Assamese V0.2.1128K / 1 GB120
Qwen2 0.5B Assamese V0.2.2128K / 1 GB70
Ymail Search Qwen2 0.5B 4bit128K / 0.5 GB90
....O.S.I.E.v4o 0.5B Stage1 Beta1128K / 1 GB111
....O.S.I.E.v4o 0.5B Stage1 Beta1128K / 1 GB51
...5 0.5B Pgabl Legal Sft Dzakwan32K / 1 GB3400
Note: green Score (e.g. "73.2") means that the model is better than kevin36524/ymail_search_qwen2-0.5B-16bit.