Velvet Eclipse 4x12B V0.2 is an open-source language model by SuperbEmphasis. Features: 38.7b LLM, VRAM: 77.7GB, Context: 1000K, MoE, LLM Explorer Score: 0.19.
Creative Dataset:superbemphasis/claude-... Dataset:superbemphasis/deepsee... Dataset:superbemphasis/deepsee... Mergekit Mixtral Moe Region:us Roleplaying Rp Safetensors Sharded Story Storywriting Tensorflow Writing
Model Card on HF 🤗: https://huggingface.co/SuperbEmphasis/Velvet-Eclipse-4x12B-v0.2
Velvet Eclipse 4x12B V0.2 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)
Velvet Eclipse 4x12B V0.2 Parameters and Internals
| LLM Name | Velvet Eclipse 4x12B V0.2 |
| Repository 🤗 | https://huggingface.co/SuperbEmphasis/Velvet-Eclipse-4x12B-v0.2 |
| Model Size | 38.7b |
| Required VRAM | 77.7 GB |
| Updated | 2026-05-31 |
| Maintainer | SuperbEmphasis |
| Model Type | mixtral |
| Model Files | |
| Model Architecture | MixtralForCausalLM |
| Context Length | 1024000 |
| Model Max Length | 1024000 |
| Transformers Version | 4.52.4 |
| Tokenizer Class | PreTrainedTokenizer |
| Padding Token | <s> |
| Vocabulary Size | 131072 |
| Torch Data Type | bfloat16 |
Rank the Velvet Eclipse 4x12B V0.2 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? 54290 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a