LLM EXPLORER 60,783 MODELS INDEXED

Phi 3 Mini 4K Instruct by AlekseyElygin

By AlekseyElygin · 32 downloads

Phi 3 Mini 4K Instruct is an open-source language model by AlekseyElygin. Features: LLM, VRAM: 2.3GB, License: apache-2.0, Quantized, Instruction-Based, LLM Explorer Score: 0.13.

  4bit   Conversational   En   Endpoints compatible   Gguf   Instruct   Mistral   Quantized   Region:us   Unsloth

Phi 3 Mini 4K Instruct Parameters and Internals

Model Type 
text-generation-inference, transformers, unsloth, mistral, gguf
Supported Languages 
en (high)
Training Details 
Methodology:
Trained using Unsloth and Huggingface's TRL library
Training Time:
2x faster training achieved with Unsloth
Model Architecture:
mistral
LLM NamePhi 3 Mini 4K Instruct
Repository πŸ€—https://huggingface.co/AlekseyElygin/Phi-3-mini-4k-instruct 
Base Model(s)  unsloth/phi-3-mini-4k-instruct-bnb-4bit   unsloth/phi-3-mini-4k-instruct-bnb-4bit
Required VRAM2.3 GB
Updated2026-09-10
MaintainerAlekseyElygin
Model Typemistral
Instruction-BasedYes
Model Files  7.6 GB   2.3 GB   4.1 GB
Supported Languagesen
GGUF QuantizationYes
Quantization Typegguf|4bit
Model ArchitectureAutoModel
Licenseapache-2.0

Best Alternatives to Phi 3 Mini 4K Instruct

Best Alternatives
Context / RAM
Downloads
Likes
...ixtral 8x7B Instruct V0.1 GGUF0K / 15.6 GB18491655
Dolphin 2.5 Mixtral 8x7b GGUF0K / 15.6 GB18101314
Dolphin 2.7 Mixtral 8x7b GGUF0K / 15.6 GB12812176
Phi 3 Mini 4K Instruct GGUF0K / 1.4 GB142917
Spydaz Web AI 0K / 4.4 GB1543
Dolphin 2 6 Phi 2 GGUF0K / 1.2 GB527375
Autocomplete Model0K / 4.1 GB660
...3 Mini 4k OLScience 4bitQ Gguf0K / 2.3 GB260
Dictalm2.0 Instruct GGUF0K / 4.4 GB6647
Dre Phi Gguf0K / 2.3 GB90
Note: green Score (e.g. "73.2") means that the model is better than AlekseyElygin/Phi-3-mini-4k-instruct.