StableBeluga 13B GPT is an open-source language model by aegon-h. Features: 13b LLM, VRAM: 7.3GB, Context: 4K, License: other, Quantized, HF Score: 57.1, LLM Explorer Score: 0.12, Arc: 62, HellaSwag: 82.3, MMLU: 57.7, TruthfulQA: 49.6, WinoGrande: 76.9, GSM8K: 13.8.
4-bit Dataset:conceptofmind/cot subm... Dataset:conceptofmind/flan2021... Dataset:conceptofmind/niv2 sub... Dataset:conceptofmind/t0 submi... En Gptq Llama Pytorch Quantized Region:us
Model Card on HF 🤗: https://huggingface.co/aegon-h/StableBeluga-13B-GPT
StableBeluga 13B GPT Benchmarks
ARC: 62.03 vs 96.7 (so35)-35.9%
HellaSwag: 82.27 vs 95.3 (gpt4)-13.7%
MMLU: 57.71 vs 88.3 (so35)-34.6%
TruthfulQA: 49.61 vs 59 (gpt4)-15.9%
WinoGrande: 76.87 vs 87.5 (gpt4)-12.1%
GSM8K: 13.8 vs 96.4 (so35)-85.7%
LLME Score: 0.11511
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)
StableBeluga 13B GPT Parameters and Internals
| Model Type |
| |
| Supported Languages |
|
| LLM Name | StableBeluga 13B GPT |
| Repository 🤗 | https://huggingface.co/aegon-h/StableBeluga-13B-GPT |
| Model Name | StableBeluga 13B |
| Model Creator | Stability AI |
| Base Model(s) | |
| Model Size | 13b |
| Required VRAM | 7.3 GB |
| Updated | 2025-12-24 |
| Maintainer | aegon-h |
| Model Type | llama |
| Model Files | |
| Supported Languages | en |
| GPTQ Quantization | Yes |
| Quantization Type | gptq |
| Model Architecture | LlamaForCausalLM |
| License | other |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.32.1 |
| 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 StableBeluga 13B GPT
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Yarn Llama 2 13B 128K GPTQ | 128K / 7.3 GB | 17 | 16 |
| LongAlign 13B 64K GPTQ | 64K / 7.3 GB | 5 | 1 |
| ...boros L2 13B 2 1 YaRN 64K GPTQ | 64K / 7.3 GB | 12 | 3 |
| Yarn Llama 2 13B 64K GPTQ | 64K / 7.3 GB | 3 | 1 |
| OrcaMaid V3 13B 32K GPTQ | 32K / 7.3 GB | 12 | 3 |
| OrcaMaid V2 FIX 13B 32K GPTQ | 32K / 7.3 GB | 6 | 4 |
| EverythingLM 13B 16K GPTQ | 16K / 7.3 GB | 26 | 14 |
| LlongOrca 13B 16K GPT | 16K / 7.3 GB | 7 | 0 |
| Tinybra 13B GPTQ 32g 4BIT | 16K / 8 GB | 1 | 1 |
| Tinybra 13B GPTQ 4BIT | 16K / 7 GB | 5 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than aegon-h/StableBeluga-13B-GPT .
Rank the StableBeluga 13B GPT 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