LLM EXPLORER 55,709 MODELS INDEXED

GPT Oss 13.7B Specialized All Pruned MoE Only 20 Experts by AmanPriyanshu

By AmanPriyanshu · 8 downloads
HF Repo ↗ Copy URL

GPT Oss 13.7B Specialized All Pruned MoE Only 20 Experts is an open-source language model by AmanPriyanshu. Features: 13.7b LLM, VRAM: 27.2GB, Context: 128K, License: apache-2.0, MoE, LLM Explorer Score: 0.2.

  All   Conversational Dataset:amanpriyanshu/gpt-oss-...   Domain-specific   Efficient   En   Expert-pruning   Gpt-oss   Gpt oss   Mixture-of-experts   Moe   Openai   Pruned-model   Pytorch   Reasoning   Region:us   Safetensors   Sharded   Specialized   Tensorflow
Model Card on HF 🤗: https://huggingface.co/AmanPriyanshu/gpt-oss-13.7b-specialized-all-pruned-moe-only-20-experts 

GPT Oss 13.7B Specialized All Pruned MoE Only 20 Experts Parameters and Internals

LLM NameGPT Oss 13.7B Specialized All Pruned MoE Only 20 Experts
Repository 🤗https://huggingface.co/AmanPriyanshu/gpt-oss-13.7b-specialized-all-pruned-moe-only-20-experts 
Model Size13.7b
Required VRAM27.2 GB
Updated2026-08-06
MaintainerAmanPriyanshu
Model Typegpt_oss
Model Files  1.9 GB: 1-of-18   1.4 GB: 2-of-18   1.7 GB: 3-of-18   1.4 GB: 4-of-18   1.7 GB: 5-of-18   1.4 GB: 6-of-18   1.7 GB: 7-of-18   1.4 GB: 8-of-18   1.7 GB: 9-of-18   1.4 GB: 10-of-18   1.7 GB: 11-of-18   1.4 GB: 12-of-18   1.7 GB: 13-of-18   1.4 GB: 14-of-18   1.7 GB: 15-of-18   1.4 GB: 16-of-18   1.0 GB: 17-of-18   1.2 GB: 18-of-18
Supported Languagesen
Model ArchitectureGptOssForCausalLM
Licenseapache-2.0
Context Length131072
Model Max Length131072
Transformers Version4.55.0
Padding Token<|endoftext|>
Vocabulary Size201088