KA

KAT Coder V2.5 Dev 35B A3B ABLITERATED UNCENSORED PHILADELPHIA CLASS

KatGGUF by PhillyLabsUpdated 2026-08-07
Download on Hugging Face
Parameters34.7B
Context256K
Layers40
Architectureqwen35moe
Smallest quant21.2 GB
Quick answer

KAT Coder V2.5 Dev 35B A3B ABLITERATED UNCENSORED PHILADELPHIA CLASS needs about 22.3 GB of memory at Q4_K_M (a 21.2 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 3 quants, from 21.2 GB (Q4_K_M) to 36.9 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.

35B total, 3B active Mixture of Experts model for coding and agentic workflows

KAT Coder V2.5 Dev 35B-A3B is a text‑only Mixture of Experts model based on qwen35moe architecture. It contains 35B total parameters with 3B active parameters per token. The model is released under Apache‑2.0 and includes Q4_K_M, Q5_K_M, and Q8_0 GGUF quantizations.

Good at

  • High‑quality coding generation
  • Agentic coding workflows
  • Large context handling

Limits

  • Requires large VRAM for full MoE checkpoint
  • No vision or multimodal support
  • Only text‑only usage

Best for

  • Writing complex code snippets
  • Automated coding agents
  • Large‑scale code analysis

Who it’s for. Developers and researchers needing a powerful coding model with agentic capabilities. The model is suitable for environments that can handle its memory demands and require text‑only interactions.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M21.2 GB 22.3 GB
Too big Get file →
Q5_K_M24.7 GB 25.9 GB
Too big Get file →
Q8_036.9 GB 38.1 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (21.17 GB file, ~22.3 GB memory at 8k context). For 12 GB VRAM, Q5_K_M (24.73 GB file, ~25.9 GB memory). For 16 GB or more, Q8_0 (36.9 GB file, ~38.1 GB memory).

What GPU do you need for KAT Coder V2.5 Dev 35B A3B ABLITERATED UNCENSORED PHILADELPHIA CLASS?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: the best quant that fits is Q4_K_M (21.2 GB file, about 22.3 GB in use).
  • 32 GB VRAM: the best quant that fits is Q5_K_M (24.7 GB file, about 25.9 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (36.9 GB file, about 38.1 GB in use).

Which KAT Coder V2.5 Dev 35B A3B ABLITERATED UNCENSORED PHILADELPHIA CLASS quant should you choose?

Q4_K_M is the usual starting point for KAT Coder V2.5 Dev 35B A3B ABLITERATED UNCENSORED PHILADELPHIA CLASS: it balances file size and quality well. Here it is a 21.2 GB file.

The Q8_0 file is 36.9 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35moe
Parameters34.7B (approximate, mixture of experts)
Active parameters3B
Layers40
Trained context262,144 tokens
KV cache (fp16)80 KB per token

Source

Quantized byPhillyLabs
FamilyKat
Licenseapache-2.0
Downloads (HF)6,787
Last updated2026-08-07

Frequently asked questions about KAT Coder V2.5 Dev 35B A3B ABLITERATED UNCENSORED PHILADELPHIA CLASS

How much VRAM does KAT Coder V2.5 Dev 35B A3B ABLITERATED UNCENSORED PHILADELPHIA CLASS need?

About 22.3 GB at Q4_K_M with an 8K context window. That is the 21.2 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run KAT Coder V2.5 Dev 35B A3B ABLITERATED UNCENSORED PHILADELPHIA CLASS on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 22.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of KAT Coder V2.5 Dev 35B A3B ABLITERATED UNCENSORED PHILADELPHIA CLASS GGUF?

It depends on the quant: Q4_K_M is 21.2 GB, Q5_K_M is 24.7 GB, Q8_0 is 36.9 GB.

What context length does KAT Coder V2.5 Dev 35B A3B ABLITERATED UNCENSORED PHILADELPHIA CLASS support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.7 GB at 8K and 2.7 GB at 32K.

Where can I download KAT Coder V2.5 Dev 35B A3B ABLITERATED UNCENSORED PHILADELPHIA CLASS GGUF?

The files are on Hugging Face in the PhillyLabs/KAT-Coder-V2.5-Dev-35B-A3B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does KAT Coder V2.5 Dev 35B A3B ABLITERATED UNCENSORED PHILADELPHIA CLASS use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run KAT Coder V2.5 Dev on 8 GB VRAM?

Only the Q4_K_M quantization can fit, but it still requires ~22 GB memory at 8k context, so 8 GB VRAM is insufficient.

Does the model support vision or multimodal inputs?

No, the release contains only text‑only weights; vision components are not included.

What license applies to this model?

The model is released under the Apache‑2.0 license, inherited from its parent.

Other GGUFs of KAT-Coder-V2.5-Dev

Similar models

Browse all →

More from PhillyLabs

All by PhillyLabs →

More Kat models

All Kat →

Other large models

All large models →