ktm3 needs about 6.0 GB of memory at Q4_K_M (a 3.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 2 quants, from 3.7 GB (Q4_K_M) to 11.9 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 7.2 GB.
ktm3 is a 5.94B-parameter Ktm model in GGUF format, quantized by sevka-k1. Its trained context length is 256K tokens. The repository has 2 quant files, from 3.7 GB (Q4_K_M) to 11.9 GB.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 3.7 GB | 6.0 GB | Fits | Get file → | |
| — | 11.9 GB | 14.2 GB | Too big | Get file → |
What GPU do you need for ktm3?
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: the best quant that fits is Q4_K_M (3.7 GB file, about 6.0 GB in use).
- 8 GB VRAM: the best quant that fits is Q4_K_M (3.7 GB file, about 6.0 GB in use).
- 12 GB VRAM: the best quant that fits is Q4_K_M (3.7 GB file, about 6.0 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (11.9 GB file, about 14.2 GB in use).
Which ktm3 quant should you choose?
Q4_K_M is the usual starting point for ktm3: it balances file size and quality well. Here it is a 3.7 GB file.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about ktm3
How much VRAM does ktm3 need?
About 6.0 GB at Q4_K_M with an 8K context window. That is the 3.7 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 ktm3 on an 8 GB GPU?
Yes, with Q4_K_M: the 3.7 GB file needs about 6.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of ktm3 GGUF?
It depends on the quant: Q4_K_M is 3.7 GB, file is 11.9 GB.
What context length does ktm3 support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.8 GB at 8K and 7.2 GB at 32K.
Where can I download ktm3 GGUF?
The files are on Hugging Face in the sevka-k1/ktm3 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.