LLM EXPLORER 61,561 MODELS INDEXED

Phi 4 Mini Instruct W4a16 Llmcompressor by amd

By amd · 191 downloads
HF Repo ↗ Copy URL

Phi 4 Mini Instruct W4a16 Llmcompressor is an open-source language model by amd. Features: 3.8b LLM, VRAM: 2.9GB, Context: 128K, License: mit, Instruction-Based, LLM Explorer Score: 0.28.

  4-bit   Amd Base model:microsoft/phi-4-min... Base model:quantized:microsoft...   Compressed-tensors   Conversational   Cpu-inference   Custom code   En   Endpoints compatible   Instruct   Int4   Llm-compressor   Phi3   Quantized   Region:us   Safetensors   W4a16   Weight-only   Zendnn
Model Card on HF 🤗: https://huggingface.co/amd/Phi-4-mini-instruct-w4a16-llmcompressor 

Phi 4 Mini Instruct W4a16 Llmcompressor Parameters and Internals

LLM NamePhi 4 Mini Instruct W4a16 Llmcompressor
Repository 🤗https://huggingface.co/amd/Phi-4-mini-instruct-w4a16-llmcompressor 
Base Model(s)  Phi 4 Mini Instruct   microsoft/Phi-4-mini-instruct
Model Size3.8b
Required VRAM2.9 GB
Updated2026-09-18
Maintaineramd
Model Typephi3
Instruction-BasedYes
Model Files  2.9 GB
Supported Languagesen
Model ArchitecturePhi3ForCausalLM
Licensemit
Context Length131072
Model Max Length131072
Transformers Version5.10.1
Tokenizer ClassTokenizersBackend
Padding Token<|endoftext|>
Vocabulary Size200064

Best Alternatives to Phi 4 Mini Instruct W4a16 Llmcompressor

Best Alternatives
Context / RAM
Downloads
Likes
Phi 4 Mini Instruct128K / 7.7 GB514603791
Phi 3.5 Mini Instruct128K / 7.7 GB1164079999
Phi 3 Mini 128K Instruct128K / 7.7 GB2336631700
Phi 3 Mini 128K Instruct128K / 7.7 GB70
Phi 4 Mini Abliterated128K / 7.7 GB331
Phi 3 Mini 128K Instruct128K / 7.7 GB110
Phi 4 Mini Instruct Heretic128K / 7.7 GB130
Phi 3.5 Mini TitanFusion 0.1128K / 7.7 GB70
NuExtract V1.5128K / 7.7 GB10851189
MediPhi Instruct128K / 7.7 GB167169
Note: green Score (e.g. "73.2") means that the model is better than amd/Phi-4-mini-instruct-w4a16-llmcompressor.