LLM EXPLORER 58,873 MODELS INDEXED

Phi 3 Medium 128K Instruct Quantized 4bit by kamelcharaf

By kamelcharaf · 1988 downloads

Phi 3 Medium 128K Instruct Quantized 4bit is an open-source language model by kamelcharaf. Features: 7.4b LLM, VRAM: 7.7GB, Context: 128K, Quantized, Instruction-Based, LLM Explorer Score: 0.2.

  Arxiv:1910.09700   4-bit   4bit   Autotrain compatible   Bitsandbytes   Conversational   Custom code   Endpoints compatible   Instruct   Phi3   Quantized   Region:us   Safetensors   Sharded   Tensorflow

Phi 3 Medium 128K Instruct Quantized 4bit Parameters and Internals

LLM NamePhi 3 Medium 128K Instruct Quantized 4bit
Repository πŸ€—https://huggingface.co/kamelcharaf/Phi-3-medium-128k-instruct-quantized-4bit 
Model Size7.4b
Required VRAM7.7 GB
Updated2025-05-16
Maintainerkamelcharaf
Model Typephi3
Instruction-BasedYes
Model Files  4.9 GB: 1-of-2   2.8 GB: 2-of-2
Quantization Type4bit
Model ArchitecturePhi3ForCausalLM
Context Length131072
Model Max Length131072
Transformers Version4.48.3
Tokenizer ClassLlamaTokenizer
Padding Token<|endoftext|>
Vocabulary Size32064
Torch Data Typefloat16