LLM EXPLORER 57,918 MODELS INDEXED

QiMing MoE 20B MXFP4 by aifeifei798

By aifeifei798 · 4 downloads
HF Repo ↗ Copy URL

QiMing MoE 20B MXFP4 is an open-source language model by aifeifei798. Features: 1.8b LLM, VRAM: 13.4GB, Context: 128K, License: apache-2.0, MoE, LLM Explorer Score: 0.2.

  8-bit   Base model:openai/gpt-oss-20b Base model:quantized:openai/gp...   Conversational   Doi:10.57967/hf/7575   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 Parameters and Internals

LLM NameQiMing MoE 20B MXFP4
Repository 🤗https://huggingface.co/aifeifei798/QiMing-Moe-20B-MXFP4 
Base Model(s)  GPT Oss 20B   openai/gpt-oss-20b
Model Size1.8b
Required VRAM13.4 GB
Updated2026-07-04
Maintaineraifeifei798
Model Typegpt_oss
Model Files  1.2 GB: 1-of-15   1.0 GB: 2-of-15   1.2 GB: 3-of-15   1.0 GB: 4-of-15   1.0 GB: 5-of-15   0.8 GB: 6-of-15   0.8 GB: 7-of-15   0.8 GB: 8-of-15   0.8 GB: 9-of-15   0.8 GB: 10-of-15   0.8 GB: 11-of-15   0.8 GB: 12-of-15   0.8 GB: 13-of-15   0.8 GB: 14-of-15   0.8 GB: 15-of-15
Supported Languagesen
Model ArchitectureGptOssForCausalLM
Licenseapache-2.0
Context Length131072
Model Max Length131072
Transformers Version4.56.1
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|endoftext|>
Vocabulary Size201088