Tenebra 30B ARM needs about 31.9 GB of memory at Q4_0 (a 18.4 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 2 quants, from 18.4 GB (Q4_0) to 18.4 GB (Q4_0).
Tenebra 30B ARM is a 32.5B-parameter Tenebra model in GGUF format, quantized by SicariusSicariiStuff. Its trained context length is 16K tokens. The repository has 2 quant files, from 18.4 GB (Q4_0) to 18.4 GB (Q4_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_0 | 18.4 GB | 31.9 GB | Too big | Get file → | |
| Q4_0 | 18.4 GB | 31.9 GB | Too big | Get file → |
What GPU do you need for Tenebra 30B ARM?
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: the best quant that fits is Q4_0 (18.4 GB file, about 31.9 GB in use).
Which Tenebra 30B ARM quant should you choose?
Q4_0 (18.4 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Tenebra 30B ARM
How much VRAM does Tenebra 30B ARM need?
About 31.9 GB at Q4_0 with an 8K context window. That is the 18.4 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 Tenebra 30B ARM on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 31.9 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Tenebra 30B ARM GGUF?
It depends on the quant: Q4_0 is 18.4 GB, Q4_0 is 18.4 GB.
What context length does Tenebra 30B ARM support?
The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 13.1 GB at 8K and 26.2 GB at 16K.
Where can I download Tenebra 30B ARM GGUF?
The files are on Hugging Face in the SicariusSicariiStuff/Tenebra_30B_ARM repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Tenebra 30B ARM 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.