KAT Codex V2.5 Dev 48Gb needs about 42.5 GB of memory at Q8_0 (a 37.5 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 3 quants, from 0.1 GB to 39.2 GB (Q8_0).
KAT Codex V2.5 Dev 48Gb is a 34.7B-parameter Kat model in GGUF format, quantized by AlexanderKyng. Its trained context length is 256K tokens. The repository has 3 quant files, from 0.1 GB to 39.2 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q8_0 | 37.5 GB | 42.5 GB | Too big | Get file → | |
| Q8_0 | 39.2 GB | 44.4 GB | Too big | Get file → |
What GPU do you need for KAT Codex V2.5 Dev 48Gb?
These figures add the file size, an fp16 KV cache at an 8K context window 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: the best quant that fits is the main file (0.1 GB file, about 0.6 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 0.6 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 0.6 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 0.6 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 0.6 GB in use).
- 24 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 0.6 GB in use).
- 32 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 0.6 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (39.2 GB file, about 44.4 GB in use).
Which KAT Codex V2.5 Dev 48Gb quant should you choose?
Q8_0 (37.5 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
If memory is tight, the smallest file is the first one in the table at 0.1 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about KAT Codex V2.5 Dev 48Gb
How much VRAM does KAT Codex V2.5 Dev 48Gb need?
About 42.5 GB at Q8_0 with an 8K context window. That is the 37.5 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 Codex V2.5 Dev 48Gb on an 8 GB GPU?
Yes, with the smaller files: the 0.1 GB file needs about 0.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of KAT Codex V2.5 Dev 48Gb GGUF?
It depends on the quant: file is 0.1 GB, Q8_0 is 37.5 GB, Q8_0 is 39.2 GB.
What context length does KAT Codex V2.5 Dev 48Gb support?
The GGUF header lists a trained context length of 262,144 tokens (256K).
Where can I download KAT Codex V2.5 Dev 48Gb GGUF?
The files are on Hugging Face in the AlexanderKyng/KAT-Codex-V2.5-Dev-48Gb 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 Codex V2.5 Dev 48Gb 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.