Arxiv:2010.04245 Arxiv:2108.12409 Arxiv:2205.14135 Codegen Composer Ggml Instruct Llm-foundry Mosaicml Mpt Quantized Region:us
Model Card on HF 🤗: https://huggingface.co/TheBloke/mpt-30B-chat-GGML
Mpt 30B Chat GGML 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)
Mpt 30B Chat GGML Parameters and Internals
| LLM Name | Mpt 30B Chat GGML |
| Repository 🤗 | https://huggingface.co/TheBloke/mpt-30B-chat-GGML |
| Model Size | 30b |
| Required VRAM | 16.9 GB |
| Updated | 2026-01-30 |
| Maintainer | TheBloke |
| Model Type | mpt |
| Instruction-Based | Yes |
| Model Files | |
| GGML Quantization | Yes |
| Quantization Type | ggml |
| Generates Code | Yes |
| Model Architecture | AutoModel |
| License | cc-by-nc-sa-4.0 |
Rank the Mpt 30B Chat GGML 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? 51611 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124