CrabSoup needs about 68.9 GB of memory at Q4_K_S (a 66.9 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 3 quants, from 66.9 GB (Q4_K_S) to 66.9 GB (Q4_K_S). Longer context needs more: at 32K tokens the KV cache alone adds about 6.3 GB.
CrabSoup is a 110B-parameter Crabsoup model in GGUF format, quantized by concedo. Its trained context length is 128K tokens. The repository has 3 quant files, from 66.9 GB (Q4_K_S) to 66.9 GB (Q4_K_S).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_S | 66.9 GB (2 parts) | 68.9 GB | Too big | Get file → | |
| Q4_K_S | 66.9 GB (2 parts) | 68.9 GB | Too big | Get file → | |
| Q4_K_S | 66.9 GB (2 parts) | 68.9 GB | Too big | Get file → |
What GPU do you need for CrabSoup?
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: no quant fits at an 8K context.
Which CrabSoup quant should you choose?
Q4_K_S (66.9 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.
If memory is tight, the smallest file is Q4_K_S at 66.9 GB, with the quality trade-offs that come with fewer bits. 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 CrabSoup
How much VRAM does CrabSoup need?
About 68.9 GB at Q4_K_S with an 8K context window. That is the 66.9 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 CrabSoup on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 68.9 GB, so you would need a larger GPU or CPU offloading.
What is the file size of CrabSoup GGUF?
It depends on the quant: Q4_K_S is 66.9 GB, Q4_K_S is 66.9 GB, Q4_K_S is 66.9 GB.
What context length does CrabSoup support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.6 GB at 8K and 6.3 GB at 32K.
Where can I download CrabSoup GGUF?
The files are on Hugging Face in the concedo/CrabSoup-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.