LLM EXPLORER 59,358 MODELS INDEXED

Phi 3 Vision Win Snap by Kukedlc

By Kukedlc · 12 downloads

Phi 3 Vision Win Snap is an open-source language model by Kukedlc. Features: 4.1b LLM, VRAM: 8.3GB, Context: 128K, License: mit, Instruction-Based, LLM Explorer Score: 0.12.

  Code   Conversational   Custom code   Instruct   Multilingual   Phi3 v   Region:us   Safetensors   Sharded   Tensorflow   Vision

Phi 3 Vision Win Snap Parameters and Internals

Model Type 
multimodal, text generation
Additional Notes 
The model underwent a rigorous enhancement process to ensure precise instruction adherence and robust safety measures.
Supported Languages 
multilingual (proficiency not specified)
Training Details 
Data Sources:
synthetic data, filtered publicly available websites
Methodology:
supervised fine-tuning and direct preference optimization
Context Length:
128000
LLM NamePhi 3 Vision Win Snap
Repository πŸ€—https://huggingface.co/Kukedlc/Phi-3-Vision-Win-snap 
Model Size4.1b
Required VRAM8.3 GB
Updated2026-08-01
MaintainerKukedlc
Model Typephi3_v
Instruction-BasedYes
Model Files  4.9 GB: 1-of-2   3.4 GB: 2-of-2
Model ArchitecturePhi3VForCausalLM
Licensemit
Context Length131072
Model Max Length131072
Transformers Version4.38.1
Tokenizer ClassLlamaTokenizer
Padding Token<|endoftext|>
Vocabulary Size32064
Torch Data Typebfloat16

Best Alternatives to Phi 3 Vision Win Snap

Best Alternatives
Context / RAM
Downloads
Likes
Phi 3.5 Vision Instruct128K / 8.3 GB1243386737
VLM2Vec Full128K / 8.3 GB57949329
Phi 3 Vision 128K Instruct128K / 8.3 GB240595973
Phi 3.5 Vision Instruct Bf16128K / 8.3 GB482
...on 128K Instruct No Flash Attn128K / 8.3 GB130
Phi 3 Vision 128K Instruct128K / 8.3 GB80
...hi 3 HornyVision 128K Instruct128K / 8.3 GB1729
Note: green Score (e.g. "73.2") means that the model is better than Kukedlc/Phi-3-Vision-Win-snap.