Autotrain compatible Base model:beberik/nyxene-v3-1... Base model:decapoda-research/a... Base model:himitsui/kaiju-11b Base model:merge:beberik/nyxen... Base model:merge:decapoda-rese... Base model:merge:himitsui/kaij... Base model:merge:sao10k/fimbul... Base model:sao10k/fimbulvetr-1... Beberik/nyxene-v3-11b Conversational Decapoda-research/antares-11b-... Endpoints compatible Frankenmoe Himitsui/kaiju-11b Merge Mergekit Mixtral Moe Region:us Safetensors Sao10k/fimbulvetr-11b-v2 Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/SteelStorage/Umbra-v3-MoE-4x11b-2ex
Umbra V3 MoE 4x11b 2ex 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)
Umbra V3 MoE 4x11b 2ex Parameters and Internals
| LLM Name | Umbra V3 MoE 4x11b 2ex |
| Repository 🤗 | https://huggingface.co/SteelStorage/Umbra-v3-MoE-4x11b-2ex |
| Base Model(s) | |
| Model Size | 36.1b |
| Required VRAM | 72.3 GB |
| Updated | 2025-09-23 |
| Maintainer | SteelStorage |
| Model Type | mixtral |
| Model Files | |
| Model Architecture | MixtralForCausalLM |
| License | apache-2.0 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.39.3 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <s> |
| Vocabulary Size | 32000 |
| Torch Data Type | bfloat16 |
Best Alternatives to Umbra V3 MoE 4x11b 2ex
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Umbra V3 MoE 4x11b 2ex | 32K / 72.3 GB | 286 | 4 |
| PiVoT MoE | 32K / 72.3 GB | 1790 | 8 |
| Umbra V3 MoE 4x11b | 32K / 72.3 GB | 5 | 5 |
| Umbra V2.1 MoE 4x10.7 | 32K / 72.3 GB | 6 | 6 |
| Mixolar 4x7b | 4K / 72.3 GB | 9780 | 3 |
| Smartsolmix 4x10.7B V1 | 4K / 72.3 GB | 1858 | 0 |
| Orca SOLAR 4x10.7B | 4K / 72.3 GB | 1738 | 0 |
| MetaModel MoE | 4K / 72.3 GB | 1914 | 0 |
| SOLARC MoE 10.7Bx4 | 4K / 144.7 GB | 1917 | 9 |
| Frankenstein MoE En 10.7Bx4 | 4K / 72.3 GB | 1915 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than SteelStorage/Umbra-v3-MoE-4x11b-2ex .
Rank the Umbra V3 MoE 4x11b 2ex 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? 51535 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124