What GPU do I need to run KridgeDookie/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS?
34.7B parameters, published in BF16. View on Hugging Face
Set up KAT-Coder-V…ILADELPHIA-CLASSKAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS is published by KridgeDookie on Hugging Face, with 18,458 downloads and 2 likes to date. It's a Qwen3_5MoeForConditionalGeneration model built for text-generation, published natively in BF16.
VRAM required & cheapest live GPU fit
Required VRAM = weight size at each precision, plus a fixed overhead for KV-cache, activations, and fragmentation. Full formula and assumptions: methodology.
| Precision | Weight size | Required VRAM | Cheapest live fit | GPUs needed | Est. $/hr (full fit) |
|---|---|---|---|---|---|
| BF16 | 64.6 GB | 77.5 GB | A100 | 1 | $1.31/hr |
| cheaper alt. | RTX 5060 Ti | 5 | $0.550/hr | ||
| FP8 (quantized) | 32.3 GB | 38.7 GB | RTX 4090 | 1 | $0.441/hr |
| cheaper alt. | RTX 5060 Ti | 3 | $0.330/hr | ||
| INT4 (quantized) | 16.1 GB | 19.4 GB | RTX A5000 | 1 | $0.176/hr |
A GPU is only matched to a row if its hardware supports that precision, and the primary recommendation is always a single-GPU fit when one exists.
INT4 requires a quantized checkpoint actually published for this model, check its Hugging Face page before relying on this row.
Cheapest way to run KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS at its published (BF16) precision: 1× A100, at $1.31/hr per GPU ($1.31/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.
KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS: common questions
Can KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS run on a single GPU?
Yes, but not on a desktop card. At BF16 it needs 77.5 GB of VRAM, more than a single 32 GB desktop card holds. The cheapest live single-card fit is a 80.0 GB A100 at $1.31/hr.
What is the least VRAM KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS can run in?
19.4 GB, at INT4 (quantized), which fits a 24 GB card, against 77.5 GB at BF16. That row assumes an INT4 checkpoint has actually been published for this model, so check its Hugging Face page before planning around it.
Does quantizing KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS lower the GPU bill?
Yes. At BF16 the cheapest live fit is one A100 at $1.31/hr. At INT4 (quantized) it drops to one RTX A5000 at $0.176/hr, provided a quantized checkpoint exists for it.
Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
Related reading: A100 pricing and specs, and The best GPUs for AI, ranked.
