LLM EXPLORER 55,709 MODELS INDEXED

GPT Oss 12.0B Specialized Science Pruned MoE Only 17 Experts by AmanPriyanshu

By AmanPriyanshu · 3 downloads
HF Repo ↗ Copy URL

GPT Oss 12.0B Specialized Science Pruned MoE Only 17 Experts is an open-source language model by AmanPriyanshu. Features: 12b LLM, VRAM: 24GB, Context: 128K, License: apache-2.0, MoE, LLM Explorer Score: 0.19.

  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   Science   Sharded   Specialized   Tensorflow
Model Card on HF 🤗: https://huggingface.co/AmanPriyanshu/gpt-oss-12.0b-specialized-science-pruned-moe-only-17-experts 

GPT Oss 12.0B Specialized Science Pruned MoE Only 17 Experts Parameters and Internals

LLM NameGPT Oss 12.0B Specialized Science Pruned MoE Only 17 Experts
Repository 🤗https://huggingface.co/AmanPriyanshu/gpt-oss-12.0b-specialized-science-pruned-moe-only-17-experts 
Model Size12b
Required VRAM24 GB
Updated2026-08-03
MaintainerAmanPriyanshu
Model Typegpt_oss
Model Files  1.8 GB: 1-of-14   1.8 GB: 2-of-14   1.8 GB: 3-of-14   1.8 GB: 4-of-14   1.8 GB: 5-of-14   1.8 GB: 6-of-14   1.8 GB: 7-of-14   1.8 GB: 8-of-14   1.8 GB: 9-of-14   1.8 GB: 10-of-14   1.8 GB: 11-of-14   1.8 GB: 12-of-14   1.2 GB: 13-of-14   1.2 GB: 14-of-14
Supported Languagesen
Model ArchitectureGptOssForCausalLM
Licenseapache-2.0
Context Length131072
Model Max Length131072
Transformers Version4.55.0
Padding Token<|endoftext|>
Vocabulary Size201088