Aguila 7B 8bit is an open-source language model by xaviviro. Features: 7b LLM, VRAM: 7.7GB, Context: 2K, Quantized, LLM Explorer Score: 0.11.
Model Card on HF 🤗: https://huggingface.co/xaviviro/aguila-7b-8bit
Aguila 7B 8bit 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)
Aguila 7B 8bit Parameters and Internals
| LLM Name | Aguila 7B 8bit |
| Repository 🤗 | https://huggingface.co/xaviviro/aguila-7b-8bit |
| Model Size | 7b |
| Required VRAM | 7.7 GB |
| Updated | 2026-03-29 |
| Maintainer | xaviviro |
| Model Type | RefinedWebModel |
| Model Files | |
| GPTQ Quantization | Yes |
| Quantization Type | gptq|8bit |
| Model Architecture | RWForCausalLM |
| Context Length | 2048 |
| Model Max Length | 2048 |
| Transformers Version | 4.35.2 |
| Is Biased | 0 |
| Vocabulary Size | 50257 |
| Torch Data Type | float16 |
Best Alternatives to Aguila 7B 8bit
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Medical Falcon 7B | 0K / 7.5 GB | 8 | 1 |
| Falcon 7B GPTQ | 0K / 4.5 GB | 6 | 1 |
| ...sst1 En 2048 Falcon 7B V3 GPTQ | 0K / 4.6 GB | 8 | 4 |
| Falcon 7B Instruct GPTQ | 0K / 5.9 GB | 207 | 68 |
| ...rilla Falcon 7B Hf V0 Autogptq | 0K / 4.6 GB | 6 | 1 |
| Falcon 7B Instruct GPTQ | 0K / 5.9 GB | 8 | 4 |
| Samantha Falcon 7B GPTQ | 0K / 4.8 GB | 6 | 12 |
| Falcon 7B Autogptq | 0K / 4.8 GB | 7 | 2 |
| Falcon 7B Instruct Autogptq | 0K / 4.8 GB | 8 | 1 |
| Falcon 7B 8bit | 0K / 7.2 GB | 9 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than xaviviro/aguila-7b-8bit .
Rank the Aguila 7B 8bit 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? 52473 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