Alpaca Elina 65B 4bit is an open-source language model by Aeala. Features: 65b LLM, VRAM: 33.5GB, Context: 2K, Quantized, HF Score: 62, LLM Explorer Score: 0.1, Arc: 65.3, HellaSwag: 85.8, MMLU: 63.4, TruthfulQA: 47.3, WinoGrande: 81.4, GSM8K: 29.
Model Card on HF 🤗: https://huggingface.co/Aeala/Alpaca-elina-65b-4bit
Alpaca Elina 65B 4bit Benchmarks
ARC: 65.27 vs 96.7 (so35)-32.5%
HellaSwag: 85.75 vs 95.3 (gpt4)-10%
MMLU: 63.42 vs 88.3 (so35)-28.2%
TruthfulQA: 47.32 vs 59 (gpt4)-19.8%
WinoGrande: 81.37 vs 87.5 (gpt4)-7%
GSM8K: 29.04 vs 96.4 (so35)-69.9%
LLME Score: 0.09732
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)
Alpaca Elina 65B 4bit Parameters and Internals
| LLM Name | Alpaca Elina 65B 4bit |
| Repository 🤗 | https://huggingface.co/Aeala/Alpaca-elina-65b-4bit |
| Base Model(s) | |
| Model Size | 65b |
| Required VRAM | 33.5 GB |
| Updated | 2026-03-29 |
| Maintainer | Aeala |
| Model Type | llama |
| Model Files | |
| Quantization Type | 4bit |
| Model Architecture | LlamaForCausalLM |
| Context Length | 2048 |
| Model Max Length | 2048 |
| Transformers Version | 4.29.0.dev0 |
| Tokenizer Class | LlamaTokenizer |
| Beginning of Sentence Token | <s> |
| End of Sentence Token | </s> |
| Unk Token | <unk> |
| Vocabulary Size | 32000 |
| Torch Data Type | float16 |
Best Alternatives to Alpaca Elina 65B 4bit
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Robin 65B V2 Fp16 | 2K / 130.4 GB | 842 | 3 |
| ...Unlocked Alpaca 65B QLoRA Fp16 | 2K / 130.4 GB | 810 | 10 |
| ...65B Gpt4 1.2 4bit 32g Actorder | 2K / 38.5 GB | 913 | 0 |
| ....4.1 PI 8192 4bit 32g Actorder | 2K / 38.5 GB | 4 | 8 |
| Enterredaas 65B 4bit 128g | 2K / 35.7 GB | 9 | 1 |
| VicUnlocked Alpaca 65B 4bit | 2K / 35.7 GB | 7 | 6 |
| Llama 65B 4bit | 2K / 34.7 GB | 4 | 2 |
| LLaMA 65B 4bit 128g | 2K / 34.7 GB | 6 | 16 |
| LLaMA 65B 4bit 32g | 2K / 38.5 GB | 7 | 10 |
| Lite Oute 1 65M Instruct | 2K / 0.3 GB | 17 | 12 |
Note: green Score (e.g. "73.2") means that the model is better than Aeala/Alpaca-elina-65b-4bit .
Rank the Alpaca Elina 65B 4bit 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