Goliath 120b SOTA needs about 39.7 GB of memory at IQ2_XS (a 34.6 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 2 quants, from 34.6 GB (IQ2_XS) to 43.1 GB (Q2_K).
Goliath 120b SOTA is a 118B-parameter Goliath model in GGUF format, quantized by tu9jn. Its trained context length is 4K tokens. The repository has 2 quant files, from 34.6 GB (IQ2_XS) to 43.1 GB (Q2_K).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_XS | 34.6 GB | 37.4 GB | Too big | Get file → | |
| Q2_K | 43.1 GB | 45.9 GB | Too big | Get file → |
What GPU do you need for Goliath 120b SOTA?
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 IQ2_XS (34.6 GB file, about 39.7 GB in use).
Which Goliath 120b SOTA quant should you choose?
IQ2_XS (34.6 GB) is the middle option in this repository. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Goliath 120b SOTA
How much VRAM does Goliath 120b SOTA need?
About 39.7 GB at IQ2_XS with an 8K context window. That is the 34.6 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 Goliath 120b SOTA on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 39.7 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Goliath 120b SOTA GGUF?
It depends on the quant: IQ2_XS is 34.6 GB, Q2_K is 43.1 GB.
What context length does Goliath 120b SOTA support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 4.6 GB at 8K and 2.3 GB at 4K.
Where can I download Goliath 120b SOTA GGUF?
The files are on Hugging Face in the tu9jn/Goliath-120b_SOTA_GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.