intfloat models
1 intfloat model from intfloat on Hugging Face, from 560M to 560M parameters, published by intfloat in F16, with a 514-token context. The smallest official model, multilingual-e5-large-instruct, needs about 1.3 GB of VRAM at its published precision; the cheapest live fit is Quadro M4000 at $0.046/hr.
Pick a size
One row per official intfloat 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 |
|---|---|---|---|---|---|---|---|
| multilingual-e5-large-instruct | 560M | 1.3 GB | 0.6 GB | 0.3 GB | Quadro M4000 | $0.046/hr | not published for this architecture |
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 |
|---|---|---|---|---|---|
| multilingual-e5-large-instruct | 560M | F16 | 1.3 GB | Quadro M4000 | $0.046/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.