ByteDance models
3 ByteDance models from ByteDance on Hugging Face, from 1.4B to 2.7B parameters, published by ByteDance in BF16, with a 64K-token context. The smallest official model, Ouro-1.4B, needs about 3.2 GB of VRAM at its published precision; the cheapest live fit is RTX 3070 at $0.088/hr.
Pick a size
One row per official ByteDance 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 |
|---|---|---|---|---|---|---|---|
| Ouro-1.4B | 1.4B | 3.2 GB | 1.6 GB | 0.8 GB | RTX 3070 | $0.088/hr | 6.0 GB |
| Ouro-2.6B-Thinking | 2.7B | 6.0 GB | 3.0 GB | 1.5 GB | RTX 3070 | $0.088/hr | 12.0 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 (3)
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| Ouro-1.4B | 1.4B | BF16 | 3.2 GB | RTX 3070 | $0.088/hr |
| Ouro-1.4B-Thinking | 1.4B | BF16 | 3.2 GB | RTX 3070 | $0.088/hr |
| Ouro-2.6B-Thinking | 2.7B | BF16 | 6.0 GB | RTX 3070 | $0.088/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.