8-bit Autotrain compatible Conversational En Endpoints compatible Gpt oss Moe Mxfp4 Qiming Region:us Safetensors Sharded Tensorflow Unsloth Vllm
Model Card on HF 🤗: https://huggingface.co/aifeifei798/QiMing-Moe-20B-MXFP4
QiMing MoE 20B MXFP4 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)
QiMing MoE 20B MXFP4 Parameters and Internals
| LLM Name | QiMing MoE 20B MXFP4 |
| Repository 🤗 | https://huggingface.co/aifeifei798/QiMing-Moe-20B-MXFP4 |
| Model Size | 1.8b |
| Required VRAM | 13.4 GB |
| Updated | 2025-09-21 |
| Maintainer | aifeifei798 |
| Model Type | gpt_oss |
| Model Files | |
| Supported Languages | en |
| Model Architecture | GptOssForCausalLM |
| License | apache-2.0 |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.56.1 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 201088 |
Rank the QiMing MoE 20B MXFP4 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? 51507 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124