Rth lm code 25b needs about 8.7 GB of memory at its main file (a 7.3 GB file) with an 8K context window, so it fits on a 12 GB GPU.
Rth lm code 25b is a 6.86B-parameter Rth model in GGUF format, quantized by RthItalia. Its trained context length is 2K tokens. The repository has 1 quant file, from 7.3 GB to 7.3 GB.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 7.3 GB | 8.0 GB | Too big | Get file → |
What GPU do you need for Rth lm code 25b?
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: 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: the best quant that fits is the main file (7.3 GB file, about 8.7 GB in use).
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Rth lm code 25b
How much VRAM does Rth lm code 25b need?
About 8.7 GB at its main file with an 8K context window. That is the 7.3 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 Rth lm code 25b on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 8.7 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Rth lm code 25b GGUF?
It depends on the quant: file is 7.3 GB.
What context length does Rth lm code 25b support?
The GGUF header lists a trained context length of 2,048 tokens (2K).
Where can I download Rth lm code 25b GGUF?
The files are on Hugging Face in the RthItalia/Rth-lm-code-25b repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Rth lm code 25b use?
Hugging Face lists the license as cc-by-nc-4.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.