Model Card on HF 🤗: https://huggingface.co/MetaIX/OpenAssistant-Llama-30b-4bit
OpenAssistant Llama 30B 4bit 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)
OpenAssistant Llama 30B 4bit Parameters and Internals
| Model Type |
| |||||||||||||||||||
| Training Details |
| |||||||||||||||||||
| Release Notes |
|
| LLM Name | OpenAssistant Llama 30B 4bit |
| Repository 🤗 | https://huggingface.co/MetaIX/OpenAssistant-Llama-30b-4bit |
| Model Size | 30b |
| Required VRAM | 16.9 GB |
| Updated | 2025-08-21 |
| Maintainer | MetaIX |
| Model Type | llama |
| Model Files | |
| GGML Quantization | Yes |
| Quantization Type | ggml|q4|4bit |
| Model Architecture | LlamaForCausalLM |
| Context Length | 2048 |
| Model Max Length | 2048 |
| Transformers Version | 4.29.0.dev0 |
| Tokenizer Class | LlamaTokenizer |
| Vocabulary Size | 32016 |
| Torch Data Type | float16 |
Best Alternatives to OpenAssistant Llama 30B 4bit
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| GPT4 X Alpasta 30B 4bit | 2K / 16.9 GB | 1988 | 68 |
| Alpacino30b | 2K / 64.1 GB | 1836 | 68 |
| Tamillama Tiny 30m | 2K / 0.1 GB | 27 | 15 |
| Bluemoonrp 30B | 2K / 17.5 GB | 1873 | 24 |
| GPT4 X Alpaca 30B 4bit | 2K / 16.9 GB | 1984 | 162 |
| Tenebra 30B Alpha01 FP16 | 16K / 65 GB | 1833 | 9 |
| Tenebra 30B Alpha01 4BIT | 16K / 19.4 GB | 1084 | 1 |
| ...nebra 30B Alpha01 EXL2 2 80bpw | 16K / 11.9 GB | 7 | 1 |
| ...nebra 30B Alpha01 EXL2 2 50bpw | 16K / 10.7 GB | 7 | 0 |
| Tenebra 30B Alpha01 EXL2 3bpw | 16K / 12.7 GB | 7 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than MetaIX/OpenAssistant-Llama-30b-4bit .
Rank the OpenAssistant Llama 30B 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? 50804 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124