Model reference · open weights
LLaMmlein_1B_prerelease is an open-weight language model from LSX-UniWue. LLaMmlein_1B_prerelease (FP32) weighs 2.2 GB; 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 LSX-UniWue/LLaMmlein_1B_prerelease model card, 2026-10-01
What it is
| Released by | LSX-UniWue |
|---|---|
| Released | 2024-10-15 |
| Parameters | 1.1B |
| VRAM | 2.2 GB for the weights |
What it runs on
| Card | Requests at once | Context max | Memory |
|---|---|---|---|
| 2K each | |||
| RTX 3060 12 GB | 192 | all 2K | 11.6 GB |
| RTX 4060 Ti 16 GB | 274 | all 2K | 15.4 GB |
| RTX 3090 24 GB | 447 | all 2K | 23.4 GB |
| RTX 4090 24 GB | 446 | all 2K | 23.4 GB |
| RTX 5090 32 GB | 612 | all 2K | 31.0 GB |
| L40S 48 GB | 893 | all 2K | 44.0 GB |
| A100 80 GB | 1000+ | all 2K | 78.2 GB |
| H100 80 GB | 1000+ | all 2K | 78.1 GB |
| RTX PRO 6000 Blackwell 96 GB | 1000+ | all 2K | 93.8 GB |
| DGX Spark (GB10) 128 GB unified | 1000+ | all 2K | 107 GB |
| H200 141 GB | 1000+ | all 2K | 138 GB |
| B200 180 GB | 1000+ | all 2K | 176 GB |
| Requests at once | 2K tokens each |
|---|---|
| 1 | 2.8 GB |
| 5 | 3.0 GB |
| 8 | 3.1 GB |
| 16 | 3.5 GB |
| 32 | 4.2 GB |
| 64 | 5.7 GB |
One card, with vLLM's small-card settings.
From the model card
This is a German Tinyllama 1B language model trained from scratch using the Tinyllama codebase on the German portion of RedPajama V2. Find more details on our page and our preprint!
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("LSX-UniWue/LLaMmlein_1B")
tokenizer = AutoTokenizer.from_pretrained("LSX-UniWue/LLaMmlein_1B")
We evaluated our results on the SuperGLEBer benchmark. Data Take Down
Quoted from the model card on Hugging Face. The full card is behind the Hugging Face link above.