Merged Model Autotrain compatible Base model:beaverai/nemoist-21... Base model:thedrummer/theia-21... Conversational Endpoints compatible Mistral Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/mergekit-community/Moist_Theia_21B
Moist Theia 21B 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)
Moist Theia 21B Parameters and Internals
| Additional Notes |
|
| LLM Name | Moist Theia 21B |
| Repository 🤗 | https://huggingface.co/mergekit-community/Moist_Theia_21B |
| Base Model(s) | |
| Merged Model | Yes |
| Model Size | 21b |
| Required VRAM | 40.8 GB |
| Updated | 2025-09-23 |
| Maintainer | mergekit-community |
| Model Type | mistral |
| Model Files | |
| Model Architecture | MistralForCausalLM |
| Context Length | 1024000 |
| Model Max Length | 1024000 |
| Transformers Version | 4.44.1 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <pad> |
| Vocabulary Size | 131072 |
| Torch Data Type | bfloat16 |
Best Alternatives to Moist Theia 21B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Theia 21B V2 | 1000K / 40.8 GB | 11 | 32 |
| Theia 21B V1 | 1000K / 40.8 GB | 3 | 30 |
| Blendy001 | 1000K / 40.8 GB | 5 | 0 |
| Theia 21B V1 Pretrained | 1000K / 40.8 GB | 5 | 0 |
| NeMoria 21B | 1000K / 40.9 GB | 32 | 12 |
| NeMoria 21B | 1000K / 40.9 GB | 5 | 12 |
| NeMoist 21B V1a | 1000K / 40.8 GB | 4 | 2 |
| NeMoist 21B V0.5 | 1000K / 40.8 GB | 5 | 0 |
| Codestral 21B Pruned | 32K / 43.1 GB | 7 | 2 |
Rank the Moist Theia 21B 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