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

 ยป  All LLMs  ยป  Jaward  ยป  Phi 3 Mini 4K Instruct.Q4 0.gguf   URL Share it on

  Arxiv:2404.14219   Autotrain compatible   Conversational   Custom code   Endpoints compatible   Gguf   Instruct   Phi3   Quantized   Region:us

Phi 3 Mini 4K Instruct.Q4 0.gguf Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Phi 3 Mini 4K Instruct.Q4 0.gguf (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 ๐Ÿค—https://huggingface.co/Jaward/phi-3-mini-4k-instruct.Q4_0.gguf 
Required VRAM2.2 GB
Updated2025-02-03
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 3 Mini 128K Instruct GGUF128K / 1.4 GB1402
...hi 3 Medium 128K Instruct GGUF128K / 5.1 GB1052
Phi 3 Mini 128K Instruct GGUF128K / 1.4 GB821
...hi 3 Medium 128K Instruct GGUF128K / 5.1 GB740
...i 3 Mini 4K Instruct IMat GGUF4K / 0.8 GB4971
Phi 3 Medium 4K Instruct GGUF4K / 5.1 GB670
Phi 3 Mini 4K Instruct GGUF4K / 1.4 GB2453
Phi 3 Medium 4K Instruct GGUF4K / 5.1 GB380
Phi 3 Mini 128K Instruct Gguf0K / 1.4 GB551
...m 128K Instruct 6.0bpw H6 EXL2128K / 10.7 GB93
Note: green Score (e.g. "73.2") means that the model is better than Jaward/phi-3-mini-4k-instruct.Q4_0.gguf.

Rank the Phi 3 Mini 4K Instruct.Q4 0.gguf Capabilities

๐Ÿ†˜ Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! ๐ŸŒŸ

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 42463 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227