Model reference · open weights
falcon-mamba-tiny-dev is an open-weight language model from tiiuae. falcon-mamba-tiny-dev (FP32) weighs 18 MB; the smallest configuration that runs it is RTX 3060 12 GB.
What it is
| Released by | tiiuae |
|---|---|
| Released | 2024-10-13 |
| Parameters | 9M |
| VRAM | 18 MB for the weights |
What it runs on
| Card | Requests at once | Context max | Memory | |
|---|---|---|---|---|
| 8K each | 32K each | |||
| RTX 3060 12 GB | 1000+ | 1000+ | 128K | 11.6 GB |
| RTX 4060 Ti 16 GB | 1000+ | 1000+ | 128K | 15.4 GB |
| RTX 3090 24 GB | 1000+ | 1000+ | 128K | 23.4 GB |
| RTX 4090 24 GB | 1000+ | 1000+ | 128K | 23.4 GB |
| RTX 5090 32 GB | 1000+ | 1000+ | 128K | 31.0 GB |
| L40S 48 GB | 1000+ | 1000+ | 128K | 44.0 GB |
| A100 80 GB | 1000+ | 1000+ | 128K | 78.2 GB |
| H100 80 GB | 1000+ | 1000+ | 128K | 78.1 GB |
| RTX PRO 6000 Blackwell 96 GB | 1000+ | 1000+ | 128K | 93.8 GB |
| DGX Spark (GB10) 128 GB unified | 1000+ | 1000+ | 128K | 107 GB |
| H200 141 GB | 1000+ | 1000+ | 128K | 138 GB |
| B200 180 GB | 1000+ | 1000+ | 128K | 176 GB |
| Requests at once | 8K tokens each | 32K tokens each |
|---|---|---|
| 1 | 518 MB | 518 MB |
| 5 | 518 MB | 518 MB |
| 8 | 518 MB | 518 MB |
| 16 | 519 MB | 519 MB |
| 32 | 519 MB | 519 MB |
| 64 | 521 MB | 521 MB |
One card, with vLLM's small-card settings.
From the model card
Tiny model for development purpose !
Quoted from the model card on Hugging Face. The full card is behind the Hugging Face link above.