defog models
1 defog model from defog on Hugging Face, from 6.7B to 6.7B parameters, published by defog in F16, with a 16K-token context. The smallest official model, sqlcoder-7b-2, needs about 15.1 GB of VRAM at its published precision; the cheapest live fit is V100 at $0.110/hr.
Pick a size
One row per official defog 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 |
|---|---|---|---|---|---|---|---|
| sqlcoder-7b-2 | 6.7B | 15.1 GB | 7.5 GB | 3.8 GB | V100 | $0.110/hr | 16.0 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 (1)
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| sqlcoder-7b-2 | 6.7B | F16 | 15.1 GB | V100 | $0.110/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.