LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  Agents   Benchmarks   LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

40K Continued Pretraining Qwen2.5 0.5B Instruct Unsloth Merged 16bit by FlofloB

 »  All LLMs  »  FlofloB  »  40K Continued Pretraining Qwen2.5 0.5B Instruct Unsloth Merged 16bit   URL Share it on

  5   

40K Continued Pretraining Qwen2.5 0.5B Instruct Unsloth Merged 16bit is an open-source language model by FlofloB. Features: 0.5b LLM, VRAM: 1.3GB, Context: 32K, License: apache-2.0, Quantized, Instruction-Based, Merged, LLM Explorer Score: 0.19.

  Merged Model   4bit   Conversational Dataset:uncovai/fineweb cc-mai...   En   Endpoints compatible   Instruct   Pytorch   Quantized   Qwen2   Region:us   Safetensors   Sft   Trl   Unsloth
Model Card on HF 🤗: https://huggingface.co/FlofloB/40k_continued_pretraining_Qwen2.5-0.5B-Instruct_Unsloth_merged_16bit 

40k Continued Pretraining Qwen2.5 0.5B Instruct Unsloth Merged 16bit Benchmarks

MMLU Pro: 5.39
GPQA: 2.35
MUSR: 1.54
BBH: 7.53
IFEval: 30.16 vs 88 (so35)-65.7%
MATH Lvl 5: 3.32
LLME Score: 0.18923
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
40K Continued Pretraining Qwen2.5 0.5B Instruct Unsloth Merged 16bit (FlofloB/40k_continued_pretraining_Qwen2.5-0.5B-Instruct_Unsloth_merged_16bit)
🌟 Advertise your project 🚀

40K Continued Pretraining Qwen2.5 0.5B Instruct Unsloth Merged 16bit Parameters and Internals

LLM Name40k Continued Pretraining Qwen2.5 0.5B Instruct Unsloth Merged 16bit
Repository 🤗https://huggingface.co/FlofloB/40k_continued_pretraining_Qwen2.5-0.5B-Instruct_Unsloth_merged_16bit 
Base Model(s)  unsloth/qwen2.5-0.5b-instruct-bnb-4bit   unsloth/qwen2.5-0.5b-instruct-bnb-4bit
Merged ModelYes
Model Size0.5b
Required VRAM1.3 GB
Updated2026-04-03
MaintainerFlofloB
Model Typeqwen2
Instruction-BasedYes
Model Files  1.3 GB   1.3 GB
Supported Languagesen
Quantization Type4bit
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.46.2
Tokenizer ClassQwen2Tokenizer
Padding Token<|PAD_TOKEN|>
Vocabulary Size151936
Torch Data Typefloat16
Errorsreplace

Best Alternatives to 40K Continued Pretraining Qwen2.5 0.5B Instruct Unsloth Merged 16bit

Best Alternatives
Context / RAM
Downloads
Likes
...0.5B Instruct Unsloth Bnb 4bit32K / 0.5 GB609584
Qwen2.5 0.5B Instruct 4bit32K / 0.3 GB150616
Qwen2.5 0.5B Instruct Bnb 4bit32K / 0.5 GB82784
TinySphinx32K / 1 GB340
...5 Coder 0.5B Instruct Bnb 4bit32K / 0.5 GB23563
... Instruct Unsloth Merged 16bit32K / 1.3 GB92
... Instruct Unsloth Merged 16bit32K / 1.3 GB82
...edCore Qwen2.5 0.5B 16bit Mini32K / 1 GB1650
... Instruct Unsloth Merged 16bit32K / 1.3 GB21
...en2.5 Coder 0.5B Instruct 4bit32K / 0.3 GB6036
Note: green Score (e.g. "73.2") means that the model is better than FlofloB/40k_continued_pretraining_Qwen2.5-0.5B-Instruct_Unsloth_merged_16bit.

Rank the 40K Continued Pretraining Qwen2.5 0.5B Instruct Unsloth Merged 16bit Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 52721 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer