LLM EXPLORER 59,358 MODELS INDEXED

Phi 3 Mini 128K Instruct Asym Int4 by unrahul

By unrahul · 122 downloads
HF Repo ↗ Copy URL

Phi 3 Mini 128K Instruct Asym Int4 is an open-source language model by unrahul. Features: LLM, VRAM: 2.5GB, Context: 128K, Instruction-Based, LLM Explorer Score: 0.12.

  Autotrain compatible   Conversational   Custom code   Endpoints compatible   Instruct   Phi3   Pytorch   Region:us
Model Card on HF 🤗: https://huggingface.co/unrahul/Phi-3-mini-128k-instruct-asym_int4 

Phi 3 Mini 128K Instruct Asym Int4 Parameters and Internals

LLM NamePhi 3 Mini 128K Instruct Asym Int4
Repository 🤗https://huggingface.co/unrahul/Phi-3-mini-128k-instruct-asym_int4 
Required VRAM2.5 GB
Updated2025-01-28
Maintainerunrahul
Model Typephi3
Instruction-BasedYes
Model Files  2.5 GB
Model ArchitecturePhi3ForCausalLM
Context Length131072
Model Max Length131072
Transformers Version4.37.0
Tokenizer ClassLlamaTokenizer
Padding Token<|endoftext|>
Vocabulary Size32064
Torch Data Typefloat32

Best Alternatives to Phi 3 Mini 128K Instruct Asym Int4

Best Alternatives
Context / RAM
Downloads
Likes
Phi 4 Mini Instruct ONNX GQA128K /  GB476
Phi 3.5 Mini Instruct Onnx128K /  GB13839
Phi 3.5 Mini Instruct Onnx Web128K /  GB40715
Phi 3 Mini 128K Instruct Onnx128K /  GB86193
...i 3 Mini 128K Instruct Ov Int4128K / 2 GB80
...Medium 128K Instruct Onnx Cuda128K /  GB8224
... Medium 128K Instruct Onnx Cpu128K /  GB8414
...um 128K Instruct Onnx Directml128K /  GB896
Meeting Model Phi3 128k128K / 7.7 GB50
Model1128K / 0.8 GB200
Note: green Score (e.g. "73.2") means that the model is better than unrahul/Phi-3-mini-128k-instruct-asym_int4.