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
Download history
daily snapshots · 56 days
▲ 50 K in the last 30 days (11.7%)
444 K338 K
Aug 23Sep 2Sep 12Sep 21
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.
| File | Quant | Size | Est. VRAM | Verdict 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 -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"
}
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
Popular comparisons