XingChen-AGI models
2 XingChen-AGI models from XingChen-AGI on Hugging Face, from 1.4B to 31.2B parameters, published by XingChen-AGI in BF16, with contexts from 125K to 256K tokens. The smallest official model, TeleOCR, 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 XingChen-AGI 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 |
|---|---|---|---|---|---|---|---|
| TeleOCR | 1.4B | 3.2 GB | 1.6 GB | 0.8 GB | RTX 3070 | $0.088/hr | 3.5 GB |
| Xing4.0-29B-A4B | 31.2B | 69.8 GB | 34.9 GB | 17.4 GB | A100 | $1.31/hr | 1.4 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 (2)
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| TeleOCR | 1.4B | BF16 | 3.2 GB | RTX 3070 | $0.088/hr |
| Xing4.0-29B-A4B | 31.2B | BF16 | 69.8 GB | A100 | $1.31/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.