KA

KAT Coder V2.5 Dev

KatGGUF by RemySkyeUpdated 2026-07-24
Download on Hugging Face
Parameters34.7B
Context256K
Layers40
Architectureqwen35moe
Smallest quant12.9 GB
Quick answer

KAT Coder V2.5 Dev 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 16 quants, from 12.9 GB (Q2_K) to 69.4 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.

KAT Coder V2.5 Dev – a 34.7B parameter, text‑only coding model

KAT Coder V2.5 Dev is a 34.7B parameter MOE model trained for coding tasks. It supports a 262144 token context and is released under the apache-2.0 license. The model is text‑only; vision components are not included.

Good at

  • Large‑scale coding
  • Agentic coding
  • SWE‑bench performance

Limits

  • No vision or multimodal support
  • Requires large VRAM for high‑quality quantizations
  • License is apache-2.0

Best for

  • Coding assistants
  • Automated code generation
  • SWE‑bench evaluation

Who it’s for. Developers and researchers needing a high‑capacity coding model for text‑only tasks. The model is suitable for environments that can allocate sufficient GPU memory and support llama.cpp quantizations.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K12.9 GB 14.1 GB
Too big Get file →
Q3_K_S15.2 GB 16.4 GB
Too big Get file →
Q3_K_M16.8 GB 17.9 GB
Too big Get file →
Q3_K_L18.1 GB 19.3 GB
Too big Get file →
IQ4_XS18.9 GB 20.1 GB
Too big Get file →
Q4_019.7 GB 20.9 GB
Too big Get file →
Q4_K_S19.9 GB 21.1 GB
Too big Get file →
Q4_K_M21.2 GB 22.3 GB
Too big Get file →
Q4_121.8 GB 23.0 GB
Too big Get file →
Q5_024.0 GB 25.2 GB
Too big Get file →
Q5_K_S24.0 GB 25.2 GB
Too big Get file →
Q5_K_M24.7 GB 25.9 GB
Too big Get file →
Q5_126.1 GB 27.3 GB
Too big Get file →
Q6_K28.5 GB 29.7 GB
Too big Get file →
Q8_036.9 GB 38.1 GB
Too big Get file →
BF1669.4 GB 70.5 GB
Too big Get file →

For 8‑GB VRAM, use Q2_K (file size 12.94 GB, ~14.1 GB memory at 8k context). For 12‑GB VRAM, Q3_K_S (15.18 GB, ~16.4 GB). For 16‑GB VRAM, Q4_K_S (19.89 GB, ~21.1 GB). Higher quants need more memory.

What GPU do you need for KAT Coder V2.5 Dev?

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: the best quant that fits is Q2_K (12.9 GB file, about 14.1 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_1 (21.8 GB file, about 23.0 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (28.5 GB file, about 29.7 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 quant should you choose?

Q4_K_M is the usual starting point for KAT Coder V2.5 Dev: 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.

If memory is tight, the smallest file is Q2_K at 12.9 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

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

Source

Quantized byRemySkye
FamilyKat
Licenseapache-2.0
Downloads (HF)1,111
Last updated2026-07-24

Frequently asked questions about KAT Coder V2.5 Dev

How much VRAM does KAT Coder V2.5 Dev 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 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 14.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of KAT Coder V2.5 Dev GGUF?

It depends on the quant: Q2_K is 12.9 GB, Q3_K_S is 15.2 GB, Q3_K_M is 16.8 GB, Q3_K_L is 18.1 GB, IQ4_XS is 18.9 GB, Q4_0 is 19.7 GB and 10 more.

What context length does KAT Coder V2.5 Dev 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 GGUF?

The files are on Hugging Face in the RemySkye/KAT-Coder-V2.5-Dev-GGUF 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 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?

The smallest quant, Q2_K, requires about 14.1 GB of VRAM at 8k context, so 8 GB is insufficient. You would need a larger GPU or a lower context size.

Does the model support image input?

No, the release ships only language‑model weights and operates as a text‑only model. Vision components are not included.

What license applies to this model?

The model is released under the apache-2.0 license.

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

Similar models

Browse all →

More from RemySkye

All by RemySkye →

More Kat models

All Kat →

Other large models

All large models →