Phi 4 Multimodal Instruct QA NoImage 0325 is an open-source language model by ntnu-smil. Features: 5.6b LLM, VRAM: 11.2GB, Context: 128K, License: mit, Instruction-Based, LLM Explorer Score: 0.19.
Base model:finetune:microsoft/... Base model:microsoft/phi-4-mul... Conversational Custom code Dataset:ntnu-smil/lttc-dev-176... Dataset:ntnu-smil/lttc-train-1... Generated from trainer Instruct Phi4mm Region:us Safetensors Sharded Tensorboard Tensorflow
Model Card on HF 🤗: https://huggingface.co/ntnu-smil/Phi-4-multimodal-instruct_QA_NoImage_0325
Phi 4 Multimodal Instruct QA NoImage 0325 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 4 Multimodal Instruct QA NoImage 0325 Parameters and Internals
| LLM Name | Phi 4 Multimodal Instruct QA NoImage 0325 |
| Repository 🤗 | https://huggingface.co/ntnu-smil/Phi-4-multimodal-instruct_QA_NoImage_0325 |
| Base Model(s) | |
| Model Size | 5.6b |
| Required VRAM | 11.2 GB |
| Updated | 2026-03-16 |
| Maintainer | ntnu-smil |
| Model Type | phi4mm |
| Instruction-Based | Yes |
| Model Files | |
| Model Architecture | Phi4MMForCausalLM |
| License | mit |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.48.2 |
| Tokenizer Class | GPT2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 200064 |
| Torch Data Type | bfloat16 |
Best Alternatives to Phi 4 Multimodal Instruct QA NoImage 0325
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Phi 4 Multimodal Instruct | 128K / 11.2 GB | 302749 | 1575 |
| ...Mm Lttc Binary Integrated 1764 | 128K / 33.6 GB | 6 | 0 |
| ...hi 4 Mm Binary QA NI 0415 1764 | 128K / 11.2 GB | 5 | 0 |
| ... Instruct QA NoImage 0325 1964 | 128K / 11.2 GB | 69 | 0 |
| ... Multimodal Instruct 0401V1 V1 | 128K / 11.2 GB | 8 | 0 |
| ... Multimodal Instruct 0401V1 V1 | 128K / 11.2 GB | 7 | 0 |
| ... Multimodal Instruct 0401V1 V1 | 128K / 11.2 GB | 6 | 0 |
| ...dal Instruct Lttc NoQA NoImage | 128K / 11.2 GB | 6 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than ntnu-smil/Phi-4-multimodal-instruct_QA_NoImage_0325 .
Rank the Phi 4 Multimodal Instruct QA NoImage 0325 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? 52721 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a