Model reference · open weights
GPT-Prompt-Expansion-Fooocus is an open-weight language model from LykosAI. GPT-Prompt-Expansion-Fooocus-v2 (BF16) weighs 351 MB; the smallest configuration that runs it is RTX 3060 12 GB.
Summary of the LykosAI/GPT-Prompt-Expansion-Fooocus-v2 model card, 2026-10-01
What it is
| Released by | LykosAI |
|---|---|
| Released | 2023-11-25 |
| VRAM | 351 MB for the weights |
What it runs on
| Card | Requests at once | Context max | Memory |
|---|---|---|---|
| 1K each | |||
| RTX 3060 12 GB | 284 | all 1K | 11.6 GB |
| RTX 4060 Ti 16 GB | 385 | all 1K | 15.4 GB |
| RTX 3090 24 GB | 596 | all 1K | 23.4 GB |
| RTX 4090 24 GB | 595 | all 1K | 23.4 GB |
| RTX 5090 32 GB | 798 | 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 | 908 MB |
| 5 | 1.1 GB |
| 8 | 1.2 GB |
| 16 | 1.5 GB |
| 32 | 2.1 GB |
| 64 | 3.3 GB |
One card, with vLLM's small-card settings.
From the model card
GPT2 Prompt Expansion model from lllyasviel/Fooocus
Third-party license terms
All trademarks, logos, and brand names are the property of their respective owners. All company, product and service names used in this website and licensed applications are for identification purposes only. Use of these names, trademarks, and brands does not imply endorsement.
Quoted from the model card on Hugging Face. The full card is behind the Hugging Face link above.