Model Card on HF 🤗: https://huggingface.co/WesPro/Wizard-Kun-Lake_3x7B-MoE
Wizard Kun Lake 3x7B MoE 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)
Sponsored By
Wizard Kun Lake 3x7B MoE Parameters and Internals
| Training Details |
|
| LLM Name | Wizard Kun Lake 3x7B MoE |
| Repository 🤗 | https://huggingface.co/WesPro/Wizard-Kun-Lake_3x7B-MoE |
| Model Size | 18.5b |
| Required VRAM | 37.1 GB |
| Updated | 2025-03-14 |
| Maintainer | WesPro |
| Model Type | mixtral |
| Model Files | |
| Model Architecture | MixtralForCausalLM |
| 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 Wizard Kun Lake 3x7B MoE
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Lumina 3.5 | 32K / 37.1 GB | 3015 | 0 |
| EastAsia 4x7B MoE Experiment | 32K / 37.1 GB | 1750 | 1 |
| Topxtral 4x7B V0.1 | 32K / 37.1 GB | 1708 | 4 |
| Hyperion 3.0 Mixtral 3x7B | 32K / 37.1 GB | 21 | 4 |
| Blitz AI MoE V0.7 | 32K / 37.1 GB | 12 | 1 |
| Blitz AI MoE V0.4 | 32K / 37.1 GB | 17 | 1 |
| HeroBophades 3x7B | 32K / 37.1 GB | 23 | 2 |
| NaruMOE 3x7B V2 | 32K / 37.1 GB | 9 | 0 |
| MoE 3x7b QA Code Inst | 32K / 37 GB | 24 | 4 |
| Pearl 3x7B | 32K / 37.1 GB | 22 | 2 |
Note: green Score (e.g. "73.2") means that the model is better than WesPro/Wizard-Kun-Lake_3x7B-MoE .
Rank the Wizard Kun Lake 3x7B MoE 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? 45005 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227