UnfilteredAI models
2 UnfilteredAI models from UnfilteredAI on Hugging Face, from 2.2B to 2.6B parameters, published by UnfilteredAI in F16 and F32, with a 4K-token context. The smallest official model, NSFW-flash, needs about 5.0 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 UnfilteredAI 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 |
|---|---|---|---|---|---|---|---|
| NSFW-flash | 2.2B | 5.0 GB | 2.5 GB | 1.3 GB | Quadro M4000 | $0.046/hr | 25.0 GB |
| NSFW-GEN-ANIME-v2 | 2.6B | 11.5 GB | 2.9 GB | 1.4 GB | V100 | $0.110/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 (2)
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| NSFW-flash | 2.2B | F16 | 5.0 GB | Quadro M4000 | $0.046/hr |
| NSFW-GEN-ANIME-v2 | 2.6B | F32 | 11.5 GB | V100 | $0.110/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.