EleutherAI / text-generation updated 3 years ago

gpt-j-6b

Name: gpt-j-6b
Author: EleutherAI

GPT-J 6B is a transformer model trained using Ben Wang's Mesh Transformer JAX. "GPT-J" refers to the class of model, while "6B" represents the number of trainable parameters.

Params

6.0 B

Context

—

Downloads 30d

304 K

Likes

1,525

Commercial use: allowed apache-2.0 Not gated 1 languages View on Hugging Face ↗

Download history

daily snapshots · 56 days

▲ 26 K in the last 30 days (9.3%)

304 K252 K

Jul 28Aug 15Sep 3Sep 21

Run it

copy-paste, exact tags checked against the Hub

~ · curl · api/v1

$ curl -s https://aimodelscomparison.com/api/v1/models/gpt-j-6b
{
  "hf_id": "EleutherAI/gpt-j-6b",
  "params_b": 6.00,
  "context_length": null,
  "license": { "id": "apache-2.0", "commercial": "yes" },
  "downloads_30d": 304393,
  "vram_estimates": [

  ],
  "updated_at": "2026-09-18T01:00:23Z"
}

est. VRAM —on RTX 4090 · 24 GBJSON API →

Specifications

Architecture: GPTJForCausalLM
Parameters: 6.0 B
Vocabulary: 50,400
Licence: apache-2.0
First seen on the Hub: 2022-03-02
Training datasets: EleutherAI/pile
Added to our catalog: 2026-07-28

Compare with any text-generation model

Popular comparisons

Qwen3-8B 12.9 M Qwen2.5-7B-Instruct 9.7 M Qwen3-4B 6.9 M Llama-3.1-8B-Instruct 5.9 M Qwen3-4B-Instruct-2507 4.0 M Qwen2.5-7B-Instruct-AWQ 3.5 M