Model Card on HF 🤗: https://huggingface.co/Lkynnn/Quantized_opt-125m
Quantized Opt 125M 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)
Quantized Opt 125M Parameters and Internals
| LLM Name | Quantized Opt 125M |
| Repository 🤗 | https://huggingface.co/Lkynnn/Quantized_opt-125m |
| Model Size | 125m |
| Required VRAM | 0.2 GB |
| Updated | 2025-09-24 |
| Maintainer | Lkynnn |
| Model Type | opt |
| Model Files | |
| GPTQ Quantization | Yes |
| Quantization Type | gptq|4bit |
| Model Architecture | OPTForCausalLM |
| License | mit |
| Context Length | 2048 |
| Model Max Length | 2048 |
| Transformers Version | 4.27.1 |
| Vocabulary Size | 50272 |
| Torch Data Type | float16 |
| Activation Function | relu |
Best Alternatives to Quantized Opt 125M
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Opt 125M Gptq | 2K / 0.1 GB | 3637 | 0 |
| Opt 125M Gptq | 2K / 0.1 GB | 5 | 0 |
| Opt 125M Gptq 4bit | 2K / 0.1 GB | 5 | 0 |
| Opt 125M Gptq 4bit | 2K / 0.1 GB | 28551 | 0 |
| Slc Opt 125M Gptq | 2K / 0.1 GB | 6 | 0 |
| Opt 125M GPTQ 2 | 2K / 0.1 GB | 6 | 1 |
| Opt 125M Gptq 4bits | 2K / 0.1 GB | 6 | 1 |
| Opt 125M Gptq | 2K / 0.1 GB | 6 | 1 |
| Opt 125M Gptq 4bit | 2K / 0.1 GB | 6 | 0 |
| Opt 125M 4bit 128g | 2K / 0.2 GB | 6 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than Lkynnn/Quantized_opt-125m .
Rank the Quantized Opt 125M 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? 51545 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124