Vanta Research Apollo V1 4B is an open-source language model by unmodeled-tyler. Features: 4b LLM, VRAM: 7.7GB, Context: 128K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.21.
Apollo Autotrain compatible Base model:adapter:microsoft/p... Base model:microsoft/phi-4-min... Conversational Custom code Dataset:anthropic/hh-rlhf Dataset:eleutherai/hendrycks m... Dataset:nvidia/helpsteer2 Dataset:nvidia/opensciencereas... Dataset:openai/collective-alig... En Endpoints compatible Instruct Lora Parameter-efficient Phi3 Phi4 Reasoning Region:us Safetensors Sharded Tensorflow Vanta-research
Model Card on HF 🤗: https://huggingface.co/unmodeled-tyler/vanta-research-apollo-v1-4b
Vanta Research Apollo V1 4B 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)
Vanta Research Apollo V1 4B Parameters and Internals
| LLM Name | Vanta Research Apollo V1 4B |
| Repository 🤗 | https://huggingface.co/unmodeled-tyler/vanta-research-apollo-v1-4b |
| Base Model(s) | |
| Model Size | 4b |
| Required VRAM | 7.7 GB |
| Updated | 2025-09-14 |
| Maintainer | unmodeled-tyler |
| Model Type | phi3 |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | en |
| Model Architecture | Phi3ForCausalLM |
| License | apache-2.0 |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.49.0 |
| Tokenizer Class | GPT2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 200064 |
| Torch Data Type | float16 |
Best Alternatives to Vanta Research Apollo V1 4B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Phi4 Mini Prose2Tags 4B | 128K / 7.7 GB | 5 | 0 |
| Calme 2.1 Phi3.5 4B | 128K / 7.7 GB | 67 | 4 |
| AURORAV0.3 4B | 128K / 7.7 GB | 25 | 3 |
| Lunar 4B | 128K / 7.7 GB | 33 | 1 |
| Phi3.5 Gutenberg 4B | 128K / 7.7 GB | 13 | 4 |
| Calme 2.3 Phi3 4B | 4K / 7.7 GB | 905 | 9 |
| Calme 2.2 Phi3 4B | 4K / 7.7 GB | 440 | 3 |
| Calme 2.1 Phi3 4B | 4K / 7.7 GB | 13 | 1 |
| Ruphi 4B | 128K / 7.6 GB | 36 | 0 |
| Phi 3.5 Mini Hyper | 128K / 7.7 GB | 8 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than unmodeled-tyler/vanta-research-apollo-v1-4b .
Rank the Vanta Research Apollo V1 4B 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? 53999 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