LLM EXPLORER 61,249 MODELS INDEXED

Phi 4 Mini Instruct Chat Mlx 16bit by SirSahOl

By SirSahOl · 320 downloads

Phi 4 Mini Instruct Chat Mlx 16bit is an open-source language model by SirSahOl. Features: 3.8b LLM, VRAM: 7.7GB, Context: 128K, License: mit, Quantized, Instruction-Based, LLM Explorer Score: 0.32.

  16bit Base model:finetune:microsoft/... Base model:microsoft/phi-4-min...   Conversational   Custom code   Instruct   Mlx   Phi3   Quantized   Region:us   Safetensors   Sharded   Tensorflow

Phi 4 Mini Instruct Chat Mlx 16bit Parameters and Internals

LLM NamePhi 4 Mini Instruct Chat Mlx 16bit
Repository πŸ€—https://huggingface.co/SirSahOl/Phi-4-mini-instruct-chat-mlx-16bit 
Base Model(s)  Phi 4 Mini Instruct   microsoft/Phi-4-mini-instruct
Model Size3.8b
Required VRAM7.7 GB
Updated2026-09-15
MaintainerSirSahOl
Model Typephi3
Instruction-BasedYes
Model Files  5.3 GB: 1-of-2   2.4 GB: 2-of-2
Quantization Type16bit
Model ArchitecturePhi3ForCausalLM
Licensemit
Context Length131072
Model Max Length131072
Transformers Version4.45.0
Tokenizer ClassTokenizersBackend
Padding Token<|endoftext|>
Vocabulary Size200064
Torch Data Typebfloat16

Best Alternatives to Phi 4 Mini Instruct Chat Mlx 16bit

Best Alternatives
Context / RAM
Downloads
Likes
Ph3 Q8128K / 4 GB130
...hi 3 Mini 4K Instruct Sft 4bit4K / 2.3 GB100
...hi 3 Mini 4K Instruct Sft 8bit4K / 4.1 GB50
Phi 4 Mini Instruct128K / 7.7 GB514603791
Phi 3.5 Mini Instruct128K / 7.7 GB1164079999
Phi 3 Mini 128K Instruct128K / 7.7 GB2336631700
Lexi Coder V4.3128K / 7.7 GB3091
...URA Eve Tactical Instruct 3.8B128K / 2.5 GB1770
Phi 4 Mini Instruct Desyced128K / 7.7 GB5140
Phi 3 Mini 128K Instruct128K / 7.7 GB70
Note: green Score (e.g. "73.2") means that the model is better than SirSahOl/Phi-4-mini-instruct-chat-mlx-16bit.