Falcon 1 models
4 Falcon 1 models from TII on Hugging Face, from 6.9B to 41.8B parameters, published by TII in BF16. The smallest official model, falcon-7b, needs about 16.1 GB of VRAM at its published precision; the cheapest live fit is RTX A5000 at $0.176/hr.
Part of the Falcon series · Next generation: Falcon3
Pick a size
One row per official Falcon 1 size: the VRAM it needs at each precision, the cheapest GPU that holds it today, and the KV cache for a 32K-token context.
| Model | Parameters | Native VRAM | FP8 VRAM | INT4 VRAM | Live GPU fit (native) | Est. $/hr | KV cache at 32K |
|---|---|---|---|---|---|---|---|
| falcon-7b | 7.2B | 16.1 GB | 8.1 GB | 4.0 GB | RTX A5000 | $0.176/hr | 0.25 GB |
| falcon-40b | 41.8B | 93.5 GB | 46.8 GB | 23.4 GB | RTX PRO 6000 | $1.38/hr | 3.8 GB |
VRAM is weights times a flat 1.2 overhead; the KV cache is a separate per-model figure at 16-bit, shown where the architecture is published. See the methodology.
Official models (3)
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| falcon-7b | 7.2B | BF16 | 16.1 GB | RTX A5000 | $0.176/hr |
| falcon-7b-instruct | 7.2B | BF16 | 16.1 GB | RTX A5000 | $0.176/hr |
| falcon-40b | 41.8B | BF16 | 93.5 GB | RTX PRO 6000 | $1.38/hr |
Fine-tunes and community models (1)
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| falcon-7b-instruct-sharded | 6.9B | F32 | 30.9 GB | V100 | $0.187/hr |
VRAM is for the precision the model is published in: the weights times a flat 1.2 overhead, with the KV cache not included. See the methodology. The fit shown is the lowest-priced single GPU type that holds the model at that precision, or the lowest-priced multi-GPU set (up to 8) when none does.
