RT

RTH-LM 25B V4 (QULP 2-bit)

RthGGUF by RthItaliaUpdated 2026-05-22
Download on Hugging Face
Parameters6.86B
Context2K
Layers128
Architecturerth-tcn
Smallest quant7.3 GB
Quick answer

RTH-LM 25B V4 (QULP 2-bit) 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 25B V4 (QULP 2-bit) 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

QuantFileEst. memoryvs VRAMResultDownload
—7.3 GB 8.0 GB
Too big Get file →

What GPU do you need for RTH-LM 25B V4 (QULP 2-bit)?

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

Architecturerth-tcn
Parameters6.86B
Layers128
Trained context2,048 tokens

Source

Quantized byRthItalia
FamilyRth
Downloads (HF)187
Last updated2026-05-22

Frequently asked questions about RTH-LM 25B V4 (QULP 2-bit)

How much VRAM does RTH-LM 25B V4 (QULP 2-bit) 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 25B V4 (QULP 2-bit) 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 25B V4 (QULP 2-bit) GGUF?

It depends on the quant: file is 7.3 GB.

What context length does RTH-LM 25B V4 (QULP 2-bit) support?

The GGUF header lists a trained context length of 2,048 tokens (2K).

Where can I download RTH-LM 25B V4 (QULP 2-bit) GGUF?

The files are on Hugging Face in the RthItalia/Rth-lm-25b repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from RthItalia

All by RthItalia →

More Rth models

All Rth →

Other small models

All small models →