EleutherAI / text-generation updated 6 months ago

pythia-14m

- Developed by: EleutherAI - Model type: Transformer-based Language Model - Language: English - Learn more: Pythia's GitHub repository for training procedure, config files, and details on how to use. See paper for more evals and implementation details. - Library: GPT-NeoX - License: Apache 2.0 - Contact: Join the EleutherAI Discord and post in #release-discussion. For general correspondence: [email protected]

Params
10 M
Context
2,048
Downloads 30d
378 K
Likes
6
Commercial use: allowed apache-2.0 Not gated SAFETENSORS 1 languages View on Hugging Face ↗

Download history

daily snapshots · 56 days
▲ 50 K in the last 30 days (11.7%)
444 K195 K
Jul 28Aug 15Sep 3Sep 21

Can you run it?

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

FileQuantSizeEst. VRAMVerdict on RTX 4090 · 24 GB
model.safetensors f16 0.0 GB 0.5 GB ✅ Runs comfortably
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/pythia-14m
{
  "hf_id": "EleutherAI/pythia-14m",
  "params_b": 0.01,
  "context_length": 2048,
  "license": { "id": "apache-2.0", "commercial": "yes" },
  "downloads_30d": 378426,
  "vram_estimates": [
    { "quant": "f16", "gb": 0.5 }
  ],
  "updated_at": "2026-07-28T18:08:14Z"
}
est. VRAM —on RTX 4090 · 24 GBJSON API →

Specifications

Architecture
GPTNeoXForCausalLM
Parameters
10 M
Tensor type
F16
Context length
2,048
Vocabulary
50,304
Layers / heads
6 / 4
Licence
apache-2.0
First seen on the Hub
2026-02-24
Training datasets
EleutherAI/pile
Added to our catalog
2026-07-28
Compare with any text-generation model