Model Card on HF 🤗: https://huggingface.co/wcde/llama-30b-3bit-gr128
Llama 30B 3bit Gr128 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)
Llama 30B 3bit Gr128 Parameters and Internals
| Additional Notes |
|
| LLM Name | Llama 30B 3bit Gr128 |
| Repository 🤗 | https://huggingface.co/wcde/llama-30b-3bit-gr128 |
| Model Size | 30b |
| Required VRAM | 14 GB |
| Updated | 2025-09-20 |
| Maintainer | wcde |
| Model Type | llama |
| Model Files | |
| Quantization Type | 3bit |
| Model Architecture | LLaMAForCausalLM |
| Transformers Version | 4.27.0.dev0 |
| Tokenizer Class | LlamaTokenizer |
| Vocabulary Size | 32000 |
| Torch Data Type | float16 |
Best Alternatives to Llama 30B 3bit Gr128
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Llama 30B | 0K / 58.5 GB | 24 | 0 |
| Llama 30B Int4 | 0K / 17 GB | 18 | 2 |
| Llama 30B Int4 | 0K / 17 GB | 17 | 8 |
Note: green Score (e.g. "73.2") means that the model is better than wcde/llama-30b-3bit-gr128 .
Rank the Llama 30B 3bit Gr128 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? 51483 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124