LLM EXPLORER 59,420 MODELS INDEXED

Phi 3 Mini 4K Instruct Sft 8bit by StefanKrsteski

By StefanKrsteski · 5 downloads

Phi 3 Mini 4K Instruct Sft 8bit is an open-source language model by StefanKrsteski. Features: 3.8b LLM, VRAM: 4.1GB, Context: 4K, Quantized, Instruction-Based, LLM Explorer Score: 0.13.

  Arxiv:1910.09700   8-bit   8bit   Conversational   Custom code   Endpoints compatible   Gptq   Instruct   Phi3   Quantized   Region:us   Safetensors

Phi 3 Mini 4K Instruct Sft 8bit Parameters and Internals

LLM NamePhi 3 Mini 4K Instruct Sft 8bit
Repository πŸ€—https://huggingface.co/StefanKrsteski/Phi-3-mini-4k-instruct-sft-8bit 
Model Size3.8b
Required VRAM4.1 GB
Updated2026-08-05
MaintainerStefanKrsteski
Model Typephi3
Instruction-BasedYes
Model Files  4.1 GB
Quantization Type8bit
Model ArchitecturePhi3ForCausalLM
Context Length4096
Model Max Length4096
Transformers Version4.40.2
Tokenizer ClassLlamaTokenizer
Padding Token<|endoftext|>
Vocabulary Size32064
Torch Data Typefloat16

Best Alternatives to Phi 3 Mini 4K Instruct Sft 8bit

Best Alternatives
Context / RAM
Downloads
Likes
Ph3 Q8128K / 4 GB70
...hi 3 Mini 4K Instruct Sft 4bit4K / 2.3 GB100
Phi 4 Mini Instruct128K / 7.7 GB514603791
Phi 3.5 Mini Instruct128K / 7.7 GB1164079999
Phi 3 Mini 128K Instruct128K / 7.7 GB2336631700
...URA Eve Tactical Instruct 3.8B128K / 2.5 GB1770
Lexi Coder V4.3128K / 7.7 GB3091
Phi 4 Mini Instruct Desyced128K / 7.7 GB3930
Phi 3 Mini 128K Instruct128K / 7.7 GB70
Phi 3 Mini 128K Instruct128K / 7.7 GB110
Note: green Score (e.g. "73.2") means that the model is better than StefanKrsteski/Phi-3-mini-4k-instruct-sft-8bit.