Orca 2 13B GPTQ is an open-source language model by TheBloke. Features: 13b LLM, VRAM: 7.3GB, Context: 4K, License: other, Quantized, LLM Explorer Score: 0.12, Arc: 59.8, HellaSwag: 79.1, MMLU: 59.4, GSM8K: 15.5.
Orca 2 13B GPTQ Parameters and Internals
| Model Type | |
| Use Cases |
| Areas: | |
| Limitations: | | Orca 2 retains limitations such as data biases, lack of contextual understanding, and potential for misuse |
|
|
| Additional Notes | | The model is optimized for reasoning tasks and evaluated on various tasks ranging from reasoning to grounding and safety. |
|
| Training Details |
| Model Architecture: | | Finetuned version of LLAMA-2 |
|
|
| LLM Name | Orca 2 13B GPTQ |
| Repository 🤗 | https://huggingface.co/TheBloke/Orca-2-13B-GPTQ |
| Model Name | Orca 2 13B |
| Model Creator | Microsoft |
| Base Model(s) | Orca 2 13B microsoft/Orca-2-13b |
| Model Size | 13b |
| Required VRAM | 7.3 GB |
| Updated | 2026-08-01 |
| Maintainer | TheBloke |
| Model Type | llama |
| Model Files | 7.3 GB |
| GPTQ Quantization | Yes |
| Quantization Type | gptq |
| Model Architecture | LlamaForCausalLM |
| License | other |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.35.0 |
| Tokenizer Class | LlamaTokenizer |
| Beginning of Sentence Token | <s> |
| End of Sentence Token | </s> |
| Unk Token | <unk> |
| Vocabulary Size | 32003 |
| Torch Data Type | float16 |
Best Alternatives to Orca 2 13B GPTQ
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Orca-2-13B-GPTQ.