Lumina 5.5 Instruct is an open-source language model by Ppoyaa. Features: 32.2b LLM, VRAM: 64.5GB, Context: 32K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.14, Arc: 68.8, HellaSwag: 86.5, MMLU: 64.3, GSM8K: 52.9.
Base model:finetune:ppoyaa/lum... Base model:ppoyaa/lumina-5-ins... Conversational Endpoints compatible Instruct Mixtral Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/Ppoyaa/Lumina-5.5-Instruct
Lumina 5.5 Instruct Benchmarks
ARC: 68.77 vs 96.7 (so35)-28.9%
HellaSwag: 86.45 vs 95.3 (gpt4)-9.3%
MMLU: 64.26 vs 88.3 (so35)-27.2%
GSM8K: 52.92 vs 96.4 (so35)-45.1%
LLME Score: 0.13935
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)
Lumina 5.5 Instruct Parameters and Internals
| Model Type |
| |||
| Training Details |
|
| LLM Name | Lumina 5.5 Instruct |
| Repository 🤗 | https://huggingface.co/Ppoyaa/Lumina-5.5-Instruct |
| Base Model(s) | |
| Model Size | 32.2b |
| Required VRAM | 64.5 GB |
| Updated | 2026-05-15 |
| Maintainer | Ppoyaa |
| Model Type | mixtral |
| Instruction-Based | Yes |
| Model Files | |
| Model Architecture | MixtralForCausalLM |
| License | apache-2.0 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.39.3 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <s> |
| Vocabulary Size | 32000 |
| Torch Data Type | bfloat16 |
Rank the Lumina 5.5 Instruct 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