Apalah needs about 16.2 GB of memory at Q6_K (a 13.6 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 8 quants, from 13.6 GB (Q6_K) to 16.0 GB (Q8_0).
Apalah is a 15B-parameter Apalah model in GGUF format, quantized by R136a1. Its trained context length is 8K tokens. The repository has 8 quant files, from 13.6 GB (Q6_K) to 16.0 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q6_K | 13.6 GB | 16.2 GB | Too big | Get file → | |
| Q6_K | 13.6 GB | 16.2 GB | Too big | Get file → | |
| Q6_K | 13.6 GB | 16.2 GB | Too big | Get file → | |
| Q6_K | 13.6 GB | 16.2 GB | Too big | Get file → | |
| Q8_0 | 16.0 GB | 18.6 GB | Too big | Get file → | |
| Q8_0 | 16.0 GB | 18.6 GB | Too big | Get file → | |
| Q8_0 | 16.0 GB | 18.6 GB | Too big | Get file → | |
| Q8_0 | 16.0 GB | 18.6 GB | Too big | Get file → |
What GPU do you need for Apalah?
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: the best quant that fits is Q8_0 (16.0 GB file, about 18.6 GB in use).
Which Apalah quant should you choose?
Q6_K (13.6 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.
If memory is tight, the smallest file is Q6_K at 13.6 GB, with the quality trade-offs that come with fewer bits. Very close to the original quality for most uses, at a clearly larger size than 4-bit.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about Apalah
How much VRAM does Apalah need?
About 16.2 GB at Q6_K with an 8K context window. That is the 13.6 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 Apalah on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 16.2 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Apalah GGUF?
It depends on the quant: Q6_K is 13.6 GB, Q6_K is 13.6 GB, Q6_K is 13.6 GB, Q6_K is 13.6 GB, Q8_0 is 16.0 GB, Q8_0 is 16.0 GB and 2 more.
What context length does Apalah support?
The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 2.1 GB at 8K and 2.1 GB at 8K.
Where can I download Apalah GGUF?
The files are on Hugging Face in the R136a1/Apalah repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.