Model reference · open weights
alias-gpt2-small-x21 is an open-weight language model from stanford-crfm. alias-gpt2-small-x21 (BF16) weighs 261 MB; the smallest configuration that runs it is RTX 3060 12 GB.
For self-hosting, compare this build's requirements below with the GPU you plan to rent.
Summary of the stanford-crfm/alias-gpt2-small-x21 model card, 2026-10-01
What it is
| Released by | stanford-crfm |
|---|---|
| Released | 2022-03-02 |
| VRAM | 261 MB for the weights |
What it runs on
| Card | Requests at once | Context max | Memory |
|---|---|---|---|
| 1K each | |||
| RTX 3060 12 GB | 287 | all 1K | 11.6 GB |
| RTX 4060 Ti 16 GB | 387 | all 1K | 15.4 GB |
| RTX 3090 24 GB | 599 | all 1K | 23.4 GB |
| RTX 4090 24 GB | 597 | all 1K | 23.4 GB |
| RTX 5090 32 GB | 801 | all 1K | 31.0 GB |
| L40S 48 GB | 1000+ | all 1K | 44.0 GB |
| A100 80 GB | 1000+ | all 1K | 78.2 GB |
| H100 80 GB | 1000+ | all 1K | 78.1 GB |
| RTX PRO 6000 Blackwell 96 GB | 1000+ | all 1K | 93.8 GB |
| DGX Spark (GB10) 128 GB unified | 1000+ | all 1K | 107 GB |
| H200 141 GB | 1000+ | all 1K | 138 GB |
| B200 180 GB | 1000+ | all 1K | 176 GB |
| Requests at once | 1K tokens each |
|---|---|
| 1 | 818 MB |
| 5 | 969 MB |
| 8 | 1.1 GB |
| 16 | 1.4 GB |
| 32 | 2.0 GB |
| 64 | 3.2 GB |
One card, with vLLM's small-card settings.
From the model card
More information needed
Developed by: Stanford CRFM
Shared by [Optional]: Stanford CRFM
Model type: Text Generation
Language(s) (NLP): More information needed
License: Apache 2.0
Parent Model: GPT-2
Resources for more information:
This model can be used for the task of Text Generation.
More information needed.
The model should not be used to intentionally create hostile or alienating environments for people.
Significant research has explored bias and fairness issues with language models (see, e.g., Sheng et al. (2021) and Bender et al. (2021)). Predictions generated by the model may include disturbing and harmful stereotypes across protected classes; identity characteristics; and sensitive, social, and occupational groups.
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
More information needed
More information needed
More information needed
More information needed
More information needed
More information needed
More information needed
More information needed
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
More information needed
More information needed
More information needed
More information needed.
BibTeX:
More information needed
APA:
More information needed
More information needed
More information needed
Stanford CRFM in collaboration with Ezi Ozoani and the Hugging Face team
More information needed
Use the code below to get started with the model.
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("stanford-crfm/alias-gpt2-small-x21")
model = AutoModelForCausalLM.from_pretrained("stanford-crfm/alias-gpt2-small-x21")
Quoted from the model card on Hugging Face. The full card is behind the Hugging Face link above.