Arxiv:1910.09700 4-bit Autotrain compatible Bitsandbytes Custom code Instruct Phi3 v Pytorch Region:us Vision
Model Card on HF 🤗: https://huggingface.co/dwb2023/phi-3-vision-128k-instruct-quantized
Phi 3 Vision 128K Instruct Quantized Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
Phi 3 Vision 128K Instruct Quantized Parameters and Internals
| LLM Name | Phi 3 Vision 128K Instruct Quantized |
| Repository 🤗 | https://huggingface.co/dwb2023/phi-3-vision-128k-instruct-quantized |
| Required VRAM | 2.4 GB |
| Updated | 2025-09-23 |
| Maintainer | dwb2023 |
| Model Type | phi3_v |
| Instruction-Based | Yes |
| Model Files | |
| Model Architecture | Phi3VForCausalLM |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.41.0 |
| Vocabulary Size | 32064 |
| Torch Data Type | float16 |
Best Alternatives to Phi 3 Vision 128K Instruct Quantized
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...3 Vision Glaucoma Diagnosis V1 | 128K / 8.3 GB | 5 | 1 |
| Phi Charts Train Test Val | 128K / 8.3 GB | 5 | 0 |
| ...Vision 128K Instruct Onnx Cuda | 128K / GB | 38 | 27 |
| ... Vision 128K Instruct Onnx Cpu | 128K / GB | 24 | 28 |
| ...28K Instruct Abliterated Alpha | 128K / 8.3 GB | 12 | 17 |
| ...on 128K Instruct Onnx Directml | 128K / GB | 10 | 8 |
Note: green Score (e.g. "73.2") means that the model is better than dwb2023/phi-3-vision-128k-instruct-quantized .
Rank the Phi 3 Vision 128K Instruct Quantized Capabilities
🆘 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! 🌟
What open-source LLMs or SLMs are you in search of? 51544 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124