cognitivecomputations yayi2 30b llama needs about 14.0 GB of memory at IQ3_S (a 13.3 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 8 quants, from 11.4 GB (Q2_K) to 16.1 GB (Q3_K_L).
cognitivecomputations yayi2 30b llama is a 30.4B-parameter Llama model in GGUF format, quantized by RichardErkhov. Its trained context length is 4K tokens. The repository has 8 quant files, from 11.4 GB (Q2_K) to 16.1 GB (Q3_K_L).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 11.4 GB | 12.0 GB | Too big | Get file → | |
| IQ3_XS | 12.6 GB | 13.2 GB | Too big | Get file → | |
| Q3_K_S | 13.3 GB | 13.9 GB | Too big | Get file → | |
| IQ3_S | 13.3 GB | 13.9 GB | Too big | Get file → | |
| IQ3_M | 13.9 GB | 14.5 GB | Too big | Get file → | |
| Q3_K | 14.8 GB | 15.4 GB | Too big | Get file → | |
| Q3_K_M | 14.8 GB | 15.4 GB | Too big | Get file → | |
| Q3_K_L | 16.1 GB | 16.7 GB | Too big | Get file → |
What GPU do you need for cognitivecomputations yayi2 30b llama?
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: the best quant that fits is Q3_K (14.8 GB file, about 15.5 GB in use).
- 24 GB VRAM: the best quant that fits is Q3_K_L (16.1 GB file, about 16.8 GB in use).
Which cognitivecomputations yayi2 30b llama quant should you choose?
IQ3_S (13.3 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
If memory is tight, the smallest file is Q2_K at 11.4 GB, with the quality trade-offs that come with fewer bits. 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
Frequently asked questions about cognitivecomputations yayi2 30b llama
How much VRAM does cognitivecomputations yayi2 30b llama need?
About 14.0 GB at IQ3_S with an 8K context window. That is the 13.3 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 cognitivecomputations yayi2 30b llama on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 12.1 GB, so you would need a larger GPU or CPU offloading.
What is the file size of cognitivecomputations yayi2 30b llama GGUF?
It depends on the quant: Q2_K is 11.4 GB, IQ3_XS is 12.6 GB, Q3_K_S is 13.3 GB, IQ3_S is 13.3 GB, IQ3_M is 13.9 GB, Q3_K is 14.8 GB and 2 more.
What context length does cognitivecomputations yayi2 30b llama support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.1 GB at 4K.
Where can I download cognitivecomputations yayi2 30b llama GGUF?
The files are on Hugging Face in the RichardErkhov/cognitivecomputations_-_yayi2-30b-llama-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.