What are the hardware requirements for Llm Jp 3 172B Instruct3?

Llm Jp 3 172B Instruct3 requires approximately 207.4 GB of VRAM and supports a context window of 4K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Llm Jp 3 172B Instruct3 and how large is it?

Llm Jp 3 172B Instruct3 is developed by llm-jp, a model with 172b 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 Llm Jp 3 172B Instruct3?

Llm Jp 3 172B Instruct3 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Llm Jp 3 172B Instruct3 by llm-jp — VRAM 207.4GB, 4K context

Name: Llm Jp 3 172B Instruct3
Author: llm-jp

Llm Jp 3 172B Instruct3 is an open-source language model by llm-jp. Features: 172b LLM, VRAM: 207.4GB, Context: 4K, License: other, LLM Explorer Score: 0.16.

Conversational En Ja Llama Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/llm-jp/llm-jp-3-172b-instruct3

Llm Jp 3 172B Instruct3 Parameters and Internals

LLM Name	Llm Jp 3 172B Instruct3
Repository 🤗	https://huggingface.co/llm-jp/llm-jp-3-172b-instruct3
Model Size	172b
Required VRAM	207.4 GB
Updated	2026-07-31
Maintainer	llm-jp
Model Type	llama
Model Files	4.1 GB: 1-of-74 4.5 GB: 2-of-74 4.9 GB: 3-of-74 4.8 GB: 4-of-74 4.5 GB: 5-of-74 4.9 GB: 6-of-74 4.8 GB: 7-of-74 4.5 GB: 8-of-74 4.9 GB: 9-of-74 4.8 GB: 10-of-74 4.5 GB: 11-of-74 4.9 GB: 12-of-74 4.8 GB: 13-of-74 4.5 GB: 14-of-74 4.9 GB: 15-of-74 4.8 GB: 16-of-74 4.5 GB: 17-of-74 4.9 GB: 18-of-74 4.8 GB: 19-of-74 4.5 GB: 20-of-74 4.9 GB: 21-of-74 4.8 GB: 22-of-74 4.5 GB: 23-of-74 4.9 GB: 24-of-74 4.8 GB: 25-of-74 4.5 GB: 26-of-74 4.9 GB: 27-of-74 4.8 GB: 28-of-74 4.5 GB: 29-of-74 4.9 GB: 30-of-74 4.8 GB: 31-of-74 4.5 GB: 32-of-74 4.9 GB: 33-of-74 4.8 GB: 34-of-74 4.5 GB: 35-of-74 4.9 GB: 36-of-74 4.8 GB: 37-of-74 4.5 GB: 38-of-74 4.9 GB: 39-of-74 4.8 GB: 40-of-74 4.5 GB: 41-of-74 4.9 GB: 42-of-74 4.8 GB: 43-of-74 4.5 GB: 44-of-74
Supported Languages	en ja
Model Architecture	LlamaForCausalLM
License	other
Context Length	4096
Model Max Length	4096
Transformers Version	4.47.0
Vocabulary Size	99840
Torch Data Type	bfloat16

Rank the Llm Jp 3 172B Instruct3 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