LLM EXPLORER 59,358 MODELS INDEXED

Phi 3 Mini 4K Instruct Ct2 Int8 by jncraton

By jncraton · 8 downloads
HF Repo ↗ Copy URL

Phi 3 Mini 4K Instruct Ct2 Int8 is an open-source language model by jncraton. Features: LLM, VRAM: 3.8GB, License: mit, Instruction-Based, LLM Explorer Score: 0.12.

  Code   Conversational   En   Endpoints compatible   Instruct   Region:us
Model Card on HF 🤗: https://huggingface.co/jncraton/Phi-3-mini-4k-instruct-ct2-int8 

Phi 3 Mini 4K Instruct Ct2 Int8 Parameters and Internals

Model Type 
text-generation, nlp
Use Cases 
Areas:
Commercial, Research
Applications:
Memory/compute constrained environments, Latency bound scenarios, Strong reasoning applications (especially code, math, and logic)
Primary Use Cases:
Building block for generative AI, Acceleration of research on language and multimodal models
Limitations:
Developers should consider common limitations and evaluate for accuracy, safety, and fairness before applying to specific use cases.
Considerations:
The model is not designed for all downstream purposes; adherence to applicable laws is recommended.
Additional Notes 
Phi-3 Mini-4K-Instruct is optimized for GPU, CPU, and Mobile with different configurations, including ONNX models.
Supported Languages 
en (Primary language for use; model performance is optimized for English.)
Training Details 
Data Sources:
Publicly available documents, newly created synthetic "textbook-like" data, supervised data
Data Volume:
3.3T tokens
Methodology:
Supervised fine-tuning and Direct Preference Optimization
Context Length:
4000
Training Time:
7 days
Hardware Used:
512 H100-80G GPUs
Model Architecture:
Dense decoder-only Transformer model with alignment to human preferences and safety guidelines.
Responsible Ai Considerations 
Fairness:
The model's quality of service may vary across different English varieties and non-English languages.
Transparency:
Developers should follow transparency best practices and inform end-users they are interacting with an AI system.
Accountability:
Developers are responsible for ensuring compliance with relevant laws and regulations; assessments for high-risk scenarios recommended.
Mitigation Strategies:
Implement feedback mechanisms and pipelines to ground responses in use-case specific, contextual information.
Input Output 
Input Format:
Best suited for chat format with structured prompts and questions.
Accepted Modalities:
text
Output Format:
Generated text in response to input
LLM NamePhi 3 Mini 4K Instruct Ct2 Int8
Repository 🤗https://huggingface.co/jncraton/Phi-3-mini-4k-instruct-ct2-int8 
Required VRAM3.8 GB
Updated2026-08-08
Maintainerjncraton
Instruction-BasedYes
Model Files  3.8 GB
Supported Languagesen
Model ArchitectureAutoModel
Licensemit
Model Max Length4096
Tokenizer ClassLlamaTokenizer
Padding Token<|endoftext|>

Best Alternatives to Phi 3 Mini 4K Instruct Ct2 Int8

Best Alternatives
Context / RAM
Downloads
Likes
...l 8x7B Instruct V0.1 Llamafile0K /  GB707618
Autotrain Umberto Proclama0K / 0.9 GB50
Mamba Python0K / 2 GB130
...l 8x7B Instruct V0.1 Llamafile0K /  GB318018
CSUMLM0K /  GB131
...hin 2.5 Mixtral 8x7b Llamafile0K /  GB1174
Instruct GPT J0K / 0 GB026
Vigogne Bloom 7b1 Instruct0K / 0.1 GB04
...a Instruction Fine Tune French0K / 0 GB04
MiniMaid L30K / 0 GB92
Note: green Score (e.g. "73.2") means that the model is better than jncraton/Phi-3-mini-4k-instruct-ct2-int8.