Model reference · open weights
Meta-Llama-3.1-bnb is an open-weight language model from fixie-ai. Meta-Llama-3.1-8B-Instruct-bnb-4bit (INT4) weighs 5.7 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.
What it is
| Released by | fixie-ai |
|---|---|
| Released | 2025-07-25 |
| Parameters | 8.2B |
| VRAM | 5.7 GB for the weights |
What it runs on
| Card | Requests at once | Context max | Memory | |
|---|---|---|---|---|
| 8K each | 32K each | |||
| RTX 3060 12 GB | 4 | 1 | 38K | 11.6 GB |
| RTX 4060 Ti 16 GB | 8 | 2 | 66K | 15.4 GB |
| RTX 3090 24 GB | 15 | 3 | 126K | 23.4 GB |
| RTX 4090 24 GB | 15 | 3 | 125K | 23.4 GB |
| RTX 5090 32 GB | 22 | 5 | all 128K | 31.0 GB |
| L40S 48 GB | 34 | 8 | all 128K | 44.0 GB |
| A100 80 GB | 66 | 16 | all 128K | 78.2 GB |
| H100 80 GB | 62 | 15 | all 128K | 78.1 GB |
| RTX PRO 6000 Blackwell 96 GB | 77 | 19 | all 128K | 93.8 GB |
| DGX Spark (GB10) 128 GB unified | 90 | 22 | all 128K | 107 GB |
| H200 141 GB | 118 | 29 | all 128K | 138 GB |
| B200 180 GB | 153 | 38 | all 128K | 176 GB |
| 2× RTX 3060 12 GB tensor parallel | 14 | 3 | 119K | 11.6 GB a card |
| Requests at once | 8K tokens each | 32K tokens each |
|---|---|---|
| 1 | 7.5 GB | 10.7 GB |
| 5 | 11.8 GB | 27.9 GB |
| 8 | 15.0 GB | 40.8 GB |
| 16 | 23.6 GB | 75.2 GB |
| 32 | 40.8 GB | 144 GB |
| 64 | 75.2 GB | 281 GB |
One card, with vLLM's small-card settings.
From the model card
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
[More Information Needed]
[More Information Needed]
[More Information Needed]
[More Information Needed]
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
Use the code below to get started with the model.
[More Information Needed]
[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]
[More Information Needed]
[More Information Needed]
Quoted from the model card on Hugging Face. The full card is behind the Hugging Face link above.