Aether 2.5 is an open-source language model by Maxilicious20. Features: 3b LLM, VRAM: 0.1GB, License: apache-2.0, Quantized, Instruction-Based, LLM Explorer Score: 0.27.
Aether Base model:adapter:qwen/qwen2.... Base model:qwen/qwen2.5-3b-ins... Conversational De En English German Gguf Instruct Lora Peft Quantized Region:us Safetensors Sft Trl
Model Card on HF 🤗: https://huggingface.co/Maxilicious20/Aether-2.5
Aether 2.5 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)
Aether 2.5 Parameters and Internals
| LLM Name | Aether 2.5 |
| Repository 🤗 | https://huggingface.co/Maxilicious20/Aether-2.5 |
| Base Model(s) | |
| Model Size | 3b |
| Required VRAM | 0.1 GB |
| Updated | 2026-08-04 |
| Maintainer | Maxilicious20 |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | de en |
| GGUF Quantization | Yes |
| Quantization Type | gguf |
| Model Architecture | AutoModel |
| License | apache-2.0 |
| Model Max Length | 131072 |
| Is Biased | none |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | o_proj|k_proj|down_proj|up_proj|gate_proj|v_proj|q_proj |
| LoRA Alpha | 32 |
| LoRA Dropout | 0.05 |
| R Param | 16 |
| Errors | replace |
Best Alternatives to Aether 2.5
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Llama32 3B En Emo V3 | 128K / 2 GB | 11 | 0 |
| Llama 3.2 3B VanRossum | 0K / 6.5 GB | 131 | 0 |
| Legal Llama3 Lora Model | 0K / 3.4 GB | 11 | 0 |
| MedQwen3B Reasoner | 0K / 6.2 GB | 235 | 13 |
| ...ma Doctor 3.2 3B Instruct GGUF | 0K / 2 GB | 992 | 7 |
| ...a Song Stream 3B Instruct GGUF | 0K / 2 GB | 329 | 6 |
| ... Sentient 3.2 3B Instruct GGUF | 0K / 2 GB | 222 | 8 |
| QwQ LCoT 3B Instruct GGUF | 0K / 1.9 GB | 36 | 7 |
| ...ma Magpie 3.2 3B Instruct GGUF | 0K / 2 GB | 102 | 2 |
| Llama 3.2 3B Instruct GGUF | 0K / 2 GB | 28 | 2 |
Rank the Aether 2.5 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? 55613 in total.
Original data from HuggingFace, Arena and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a