modelllama needs about 33.2 GB of memory at F16 (a 26.0 GB file) with an 8K context window, so it fits on a 48 GB GPU.
modelllama is a 13B-parameter Modelllama model in GGUF format, quantized by bk2000. Its trained context length is 4K tokens. The repository has 1 quant file, from 26.0 GB (F16) to 26.0 GB (F16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| F16 | 26.0 GB | 29.9 GB | Too big | Get file → |
What GPU do you need for modelllama?
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: no quant fits at an 8K context.
- 24 GB VRAM: no quant fits at an 8K context.
- 32 GB VRAM: no quant fits at an 8K context.
- 48 GB VRAM: the best quant that fits is F16 (26.0 GB file, about 33.2 GB in use).
Which modelllama quant should you choose?
F16 (26.0 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about modelllama
How much VRAM does modelllama need?
About 33.2 GB at F16 with an 8K context window. That is the 26.0 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 modelllama on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 33.2 GB, so you would need a larger GPU or CPU offloading.
What is the file size of modelllama GGUF?
It depends on the quant: F16 is 26.0 GB.
What context length does modelllama support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 6.7 GB at 8K and 3.4 GB at 4K.
Where can I download modelllama GGUF?
The files are on Hugging Face in the bk2000/modelllama repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does modelllama 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.