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

Phi 3 Mini 4K Instruct by unsloth

 »  All LLMs  »  unsloth  »  Phi 3 Mini 4K Instruct   URL Share it on

  4581   

Phi 3 Mini 4K Instruct is an open-source language model by unsloth. Features: 3.8b LLM, VRAM: 7.6GB, Context: 4K, License: mit, Instruction-Based, HF Score: 69.9, LLM Explorer Score: 0.37, ELO: 1127, Arc: 63, HellaSwag: 80.6, MMLU: 69.1, TruthfulQA: 59.9, WinoGrande: 72.7, GSM8K: 73.9.

  Conversational   En   Endpoints compatible   Instruct   Mistral   Phi   Phi3   Region:us   Safetensors   Sharded   Tensorflow   Unsloth
Model Card on HF 🤗: https://huggingface.co/unsloth/Phi-3-mini-4k-instruct 

Phi 3 Mini 4K Instruct Benchmarks

LMSys ELO: 1127 vs 1272 (so35)-11.4%
MMLU Pro: 33.68
GPQA: 9.73
MUSR: 13.12
BBH: 36.73
IFEval: 54.4 vs 88 (so35)-38.2%
ARC: 62.97 vs 96.7 (so35)-34.9%
HellaSwag: 80.61 vs 95.3 (gpt4)-15.4%
MMLU: 69.08 vs 88.3 (so35)-21.8%
TruthfulQA: 59.88 vs 59 (gpt4)1.5%
WinoGrande: 72.69 vs 87.5 (gpt4)-16.9%
GSM8K: 73.92 vs 96.4 (so35)-23.3%
MATH Lvl 5: 16.39
LLME Score: 0.36637
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Phi 3 Mini 4K Instruct (unsloth/Phi-3-mini-4k-instruct)
🌟 Advertise your project 🚀

Phi 3 Mini 4K Instruct Parameters and Internals

Model Type 
text generation, transformers
Use Cases 
Areas:
research, commercial applications
Primary Use Cases:
text generation, model finetuning
Additional Notes 
The model can be directly quantized to 4bit using 'bitsandbytes'.
LLM NamePhi 3 Mini 4K Instruct
Repository 🤗https://huggingface.co/unsloth/Phi-3-mini-4k-instruct 
Model Size3.8b
Required VRAM7.6 GB
Updated2026-04-04
Maintainerunsloth
Model Typemistral
Instruction-BasedYes
Model Files  5.0 GB: 1-of-2   2.6 GB: 2-of-2
Supported Languagesen
Model ArchitectureMistralForCausalLM
Licensemit
Context Length4096
Model Max Length4096
Transformers Version4.44.2
Tokenizer ClassLlamaTokenizer
Padding Token<|placeholder6|>
Vocabulary Size32064
Torch Data Typebfloat16

Quantized Models of the Phi 3 Mini 4K Instruct

Model
Likes
Downloads
VRAM
Scm Phi3 Q4 K M V30192 GB
Scm Phi3 Q4 K M0182 GB
Scm Phi3 Q8064 GB
Scm Phi3 Q5 K M V3062 GB
Scm Phi3 Q8 V3054 GB
Scm Phi3 16 V3057 GB
...Sentiment May 24 2024 2epoches0267 GB
...in 2.9.1 Phi 3 Kensho 4.5B AWQ073 GB
Dj Phi 3 F16 GGUF0147 GB
Dj Phi 3 3.8B 16bit067 GB

Best Alternatives to Phi 3 Mini 4K Instruct

Best Alternatives
Context / RAM
Downloads
Likes
Llama Phi 3 DoRA4K / 7.6 GB56
Empty Phi 3 Mini4K / 7.6 GB50
...ling Assistant Spanish Pofi V24K / 7.7 GB60
...i3 Short Story Merged Bfloat164K / 7.6 GB81
Phi 3 Mini 4K Instruct Orpo V24K / 14.9 GB11
... Instruct Unsloth Merged 16bit4K / 7.6 GB52
...ent V56 3 W Unknown 5 Lr 0.0024K / 7.6 GB60
...Word Problems 200K Model 16bit4K / 7.6 GB38790
... 4K Instruct Matter 0.1 Slim A4K / 7.6 GB72
...rser User V9b Epoch 7 Lr 0.0024K / 7.6 GB50

Rank the Phi 3 Mini 4K Instruct 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