XHToken models

3 XHToken models from XHToken on Hugging Face, from 1.7B to 4.1B parameters, published by XHToken in BF16, with a 1M-token context. The smallest official model, Spark-X2.5-1.7B, needs about 3.8 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 XHToken size: the VRAM it needs at each precision, the cheapest GPU that holds it today, and the KV cache for a 32K-token context.

ModelParametersNative VRAMFP8 VRAMINT4 VRAMLive GPU fit (native)Est. $/hrKV cache at 32K
Spark-X2.5-1.7B1.7B3.8 GB1.9 GB1.0 GBRTX 3070$0.088/hr0.46 GB
Spark-X2.6-4B4.1B9.2 GB4.6 GB2.3 GBRTX A4000$0.137/hr1.2 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)

ModelParametersPublished asVRAM neededLive GPU fitEst. $/hr
Spark-X2.5-1.7B1.7BBF163.8 GBRTX 3070$0.088/hr
Spark-X2.5-4B4.1BBF169.2 GBRTX A4000$0.137/hr
Spark-X2.6-4B4.1BBF169.2 GBRTX A4000$0.137/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.

Start ComfyUI on a rented GPU.

© 2026 Aquanode. All rights reserved.

All trademarks, logos and brand names are the property of their respective owners.