LLM EXPLORER 60,147 MODELS INDEXED

Phi 3 Medium 4K Instruct Bnb 4bit by unsloth

By unsloth · 335 downloads
HF Repo ↗ Copy URL

Phi 3 Medium 4K Instruct Bnb 4bit is an open-source language model by unsloth. Features: 14.4b LLM, VRAM: 7.7GB, Context: 4K, License: mit, Quantized, Instruction-Based, LLM Explorer Score: 0.13.

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

Phi 3 Medium 4K Instruct Bnb 4bit Parameters and Internals

Model Type 
quantized 4bit model
Use Cases 
Primary Use Cases:
text completion, conversational templates
LLM NamePhi 3 Medium 4K Instruct Bnb 4bit
Repository 🤗https://huggingface.co/unsloth/Phi-3-medium-4k-instruct-bnb-4bit 
Model Size14.4b
Required VRAM7.7 GB
Updated2026-07-28
Maintainerunsloth
Model Typemistral
Instruction-BasedYes
Model Files  5.0 GB: 1-of-2   2.7 GB: 2-of-2
Supported Languagesen
Quantization Type4bit
Model ArchitectureMistralForCausalLM
Licensemit
Context Length4096
Model Max Length4096
Transformers Version4.52.4
Tokenizer ClassLlamaTokenizer
Padding Token<|placeholder6|>
Vocabulary Size32064
Torch Data Typebfloat16

Quantized Models of the Phi 3 Medium 4K Instruct Bnb 4bit

Model
Likes
Downloads
VRAM
TofuTune Phi3 Medium Gguf0118 GB