Model reference · open weights
Qwen3-Fast is an open-weight language model from PrimeIntellect. Qwen3-30B-A3B-Base-Fast (BF16) weighs 61.1 GB; the smallest configuration that runs it is H100 80 GB.
What it is
| Released by | PrimeIntellect |
|---|---|
| Released | 2025-09-22 |
| Parameters | 30.5B |
| VRAM | 61.1 GB for the weights |
What it runs on
| Card | Requests at once | Context max | Memory | |
|---|---|---|---|---|
| 8K each | 32K each | |||
| RTX 3060 12 GB … L40S 48 GB 6 smaller cards | — | — | — | |
| A100 80 GB | 19 | 4 | all 40K | 78.2 GB |
| H100 80 GB | 12 | 3 | all 40K | 78.1 GB |
| RTX PRO 6000 Blackwell 96 GB | 32 | 8 | all 40K | 93.8 GB |
| DGX Spark (GB10) 128 GB unified | 49 | 12 | all 40K | 107 GB |
| H200 141 GB | 87 | 21 | all 40K | 138 GB |
| B200 180 GB | 131 | 32 | all 40K | 176 GB |
| 2× L40S 48 GB tensor parallel | 30 | 7 | all 40K | 44.0 GB a card |
| 4× RTX 4090 24 GB tensor parallel | 34 | 8 | all 40K | 23.4 GB a card |
| 4× RTX 3090 24 GB tensor parallel | 34 | 8 | all 40K | 23.4 GB a card |
| 4× RTX 5090 32 GB tensor parallel | 72 | 18 | all 40K | 31.0 GB a card |
| 2× H100 80 GB tensor parallel | 101 | 25 | all 40K | 78.1 GB a card |
| Requests at once | 8K tokens each | 32K tokens each |
|---|---|---|
| 1 | 63.0 GB | 65.4 GB |
| 5 | 66.2 GB | 78.3 GB |
| 8 | 68.6 GB | 88.0 GB |
| 16 | 75.1 GB | 114 GB |
| 32 | 88.0 GB | 165 GB |
| 64 | 114 GB | 268 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.