SeaPhi3 Medium is an open-source language model by SeacomSrl. Features: 14.2b LLM, VRAM: 8.4GB, Context: 4K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.16.
4-bit Bitsandbytes Conversational Dataset:seacomsrl/rag-data Deploy:azure Endpoints compatible Instruct It Mistral Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/SeacomSrl/SeaPhi3-medium
SeaPhi3 Medium 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)
SeaPhi3 Medium Parameters and Internals
| LLM Name | SeaPhi3 Medium |
| Repository 🤗 | https://huggingface.co/SeacomSrl/SeaPhi3-medium |
| Model Size | 14.2b |
| Required VRAM | 8.4 GB |
| Updated | 2026-03-29 |
| Maintainer | SeacomSrl |
| Model Type | mistral |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | it |
| Model Architecture | MistralForCausalLM |
| License | apache-2.0 |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.41.1 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 32064 |
| Torch Data Type | float16 |
Best Alternatives to SeaPhi3 Medium
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| TheTop 5x7B Instruct P V0.1 | 32K / 28.6 GB | 108 | 0 |
Rank the SeaPhi3 Medium 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