EleutherAI / text-generation updated 2 years ago

gpt-neox-20b

Name: gpt-neox-20b
Author: EleutherAI

GPT-NeoX-20B is a 20 billion parameter autoregressive language model trained on the Pile using the GPT-NeoX library. Its architecture intentionally resembles that of GPT-3, and is almost identical to that of GPT-J- 6B. Its training dataset contains a multitude of English-language texts, reflecting the general-purpose nature of this model. See the accompanying paper for details about model architecture (including how...

Params

20.7 B

Context

2,048

Downloads 30d

927 K

Likes

584

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

Download history

daily snapshots · 10 days

928 K881 K

Jul 28Jul 31Aug 3Aug 6

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
model.safetensors	f16	41.3 GB	49.0 GB	❌ Won’t fit

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Run it

copy-paste, exact tags checked against the Hub

~ · curl · api/v1

$ curl -s https://aimodelscomparison.com/api/v1/models/gpt-neox-20b
{
  "hf_id": "EleutherAI/gpt-neox-20b",
  "params_b": 20.74,
  "context_length": 2048,
  "license": { "id": "apache-2.0", "commercial": "yes" },
  "downloads_30d": 926862,
  "vram_estimates": [
    { "quant": "f16", "gb": 49.0 }
  ],
  "updated_at": "2026-07-28T18:03:51Z"
}

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

Specifications

Architecture: GPTNeoXForCausalLM
Parameters: 20.7 B
Tensor type: F16
Context length: 2,048
Vocabulary: 50,432
Layers / heads: 44 / 64
Licence: apache-2.0
First seen on the Hub: 2022-04-07
Training datasets: EleutherAI/pile
Added to our catalog: 2026-07-28

Compare with

Qwen3-8B 16.3 M Qwen2.5-7B-Instruct 12.1 M Qwen3.6-35B-A3B-NVFP4 11.3 M gpt-oss-20b 8.6 M Qwen3-32B 8.3 M Llama-3.1-8B-Instruct 8.0 M

Appears in

Best open coding models Commercial-use text models Models that fit in 12 GB