taobao-mnn models
1 taobao-mnn model from taobao-mnn on Hugging Face, from 362M to 362M parameters, published by taobao-mnn in BF16, with a 40K-token context. The smallest official model, MNN-Pocket-0.3B, needs about 0.8 GB of VRAM at its published precision; the cheapest live fit is RTX 3070 at $0.132/hr.
Pick a size
One row per official taobao-mnn 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 |
|---|---|---|---|---|---|---|---|
| MNN-Pocket-0.3B | 362M | 0.8 GB | 0.4 GB | 0.2 GB | RTX 3070 | $0.132/hr | 0.44 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 |
|---|---|---|---|---|---|
| MNN-Pocket-0.3B | 362M | BF16 | 0.8 GB | RTX 3070 | $0.132/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.
