LLM EXPLORER 59,420 MODELS INDEXED

Phi 3 Mini 4K Instruct.Q4 0.gguf by Jaward

By Jaward · 2220 downloads
HF Repo ↗ Copy URL

Phi 3 Mini 4K Instruct.Q4 0.gguf is an open-source language model by Jaward. Features: LLM, VRAM: 2.2GB, Context: 128K, License: mit, Quantized, Instruction-Based, LLM Explorer Score: 0.14.

  Arxiv:2404.14219   Conversational   Custom code   Endpoints compatible   Gguf   Instruct   Phi3   Quantized   Region:us
Model Card on HF 🤗: https://huggingface.co/Jaward/phi-3-mini-4k-instruct.Q4_0.gguf 

Phi 3 Mini 4K Instruct.Q4 0.gguf Parameters and Internals

Model Type 
llama-2 architecture
Additional Notes 
4 bits quantized GGUF weight. Not supported by mlx but mlx compatible.
LLM NamePhi 3 Mini 4K Instruct.Q4 0.gguf
Repository 🤗https://huggingface.co/Jaward/phi-3-mini-4k-instruct.Q4_0.gguf 
Required VRAM2.2 GB
Updated2026-07-01
MaintainerJaward
Model Typephi3
Instruction-BasedYes
Model Files  2.2 GB
GGUF QuantizationYes
Quantization Typegguf
Model ArchitecturePhi3ForCausalLM
Licensemit
Context Length131072
Model Max Length131072
Transformers Version4.39.3
Vocabulary Size32064
Torch Data Typebfloat16

Best Alternatives to Phi 3 Mini 4K Instruct.Q4 0.gguf

Best Alternatives
Context / RAM
Downloads
Likes
Phi 4 Mini Instruct GGUF128K / 1.7 GB51764122
Phi 3 Mini 128K Instruct GGUF128K / 1.4 GB6292
...hi 3 Medium 128K Instruct GGUF128K / 5.1 GB4942
...hi 3 Medium 128K Instruct GGUF128K / 5.1 GB3170
Phi 3 Mini 128K Instruct GGUF128K / 1.4 GB1981
Phi 3 Mini 4K Instruct GGUF4K / 1.4 GB13765
...i 3 Mini 4K Instruct IMat GGUF4K / 0.8 GB9831
Phi 3 Medium 4K Instruct GGUF4K / 5.1 GB1300
Phi 3 Medium 4K Instruct GGUF4K / 5.1 GB1300
Phi 3 Mini 128K Instruct Gguf0K / 1.4 GB13461
Note: green Score (e.g. "73.2") means that the model is better than Jaward/phi-3-mini-4k-instruct.Q4_0.gguf.