What are the hardware requirements for Pinkelephant Llm 48B MoE Base?

Pinkelephant Llm 48B MoE Base requires approximately 95.4 GB of VRAM and supports a context window of 16K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Pinkelephant Llm 48B MoE Base and how large is it?

Pinkelephant Llm 48B MoE Base is developed by pinkelephantlimited, a model with 47.7b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Pinkelephant Llm 48B MoE Base?

Pinkelephant Llm 48B MoE Base is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Pinkelephant Llm 48B MoE Base by pinkelephantlimited — VRAM 95.4GB, 16K context

Name: Pinkelephant Llm 48B MoE Base
Author: pinkelephantlimited

Pinkelephant Llm 48B MoE Base is an open-source language model by pinkelephantlimited. Features: 47.7b LLM, VRAM: 95.4GB, Context: 16K, License: mit, MoE, LLM Explorer Score: 0.31.

Base-model Base model:finetune:pinkelepha... Base model:pinkelephantlimited... Custom code En Endpoints compatible Mixture-of-experts Moe Pinkelephant moe Region:us Safetensors Sparse-moe

Model Card on HF 🤗: https://huggingface.co/pinkelephantlimited/pinkelephant-llm-48b-moe-base

Pinkelephant Llm 48B MoE Base Parameters and Internals

LLM Name	Pinkelephant Llm 48B MoE Base
Repository 🤗	https://huggingface.co/pinkelephantlimited/pinkelephant-llm-48b-moe-base
Base Model(s)	pinkelephantlimited/pink-elephant-llm-14b pinkelephantlimited/pink-elephant-llm-14b
Model Size	47.7b
Required VRAM	95.4 GB
Updated	2026-08-11
Maintainer	pinkelephantlimited
Model Type	pinkelephant_moe
Model Files	95.4 GB
Supported Languages	en
License	mit
Context Length	16384
Model Max Length	16384
Transformers Version	5.14.1
Vocabulary Size	100352

Rank the Pinkelephant Llm 48B MoE Base capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation