Aquila2 70B Expr 4.0bpw H6 EXL2 is an open-source language model by LoneStriker. Features: 70b LLM, VRAM: 36.6GB, Context: 4K, License: other, Quantized, LLM Explorer Score: 0.1.
Model Card on HF 🤗: https://huggingface.co/LoneStriker/Aquila2-70B-Expr-4.0bpw-h6-exl2
Aquila2 70B Expr 4.0bpw H6 EXL2 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)
Aquila2 70B Expr 4.0bpw H6 EXL2 Parameters and Internals
| Model Type |
| |
| Supported Languages |
|
| LLM Name | Aquila2 70B Expr 4.0bpw H6 EXL2 |
| Repository 🤗 | https://huggingface.co/LoneStriker/Aquila2-70B-Expr-4.0bpw-h6-exl2 |
| Model Size | 70b |
| Required VRAM | 36.6 GB |
| Updated | 2026-07-13 |
| Maintainer | LoneStriker |
| Model Type | aquila |
| Model Files | |
| Quantization Type | exl2 |
| Model Architecture | AquilaForCausalLM |
| License | other |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.31.0 |
| Tokenizer Class | GPT2Tokenizer |
| Vocabulary Size | 100008 |
| Torch Data Type | bfloat16 |
Best Alternatives to Aquila2 70B Expr 4.0bpw H6 EXL2
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| AquilaChat2 70B Expr | 4K / 66.5 GB | 115 | 5 |
| Aquila2 70B Expr | 4K / 68.2 GB | 146 | 10 |
Note: green Score (e.g. "73.2") means that the model is better than LoneStriker/Aquila2-70B-Expr-4.0bpw-h6-exl2 .
Rank the Aquila2 70B Expr 4.0bpw H6 EXL2 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? 55346 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