Psyonic Cetacean Ultra Quality 20b needs about 22.9 GB of memory at Q4_K_M (a 12.0 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 11 quants, from 7.4 GB (Q2_K) to 21.2 GB (Q8_0).
Ultra‑quality 20B Llama model with extensive FP32 remastering
Psyonic Cetacean Ultra Quality 20b is a 20 billion‑parameter Llama model remastered to FP32 precision. It supports roleplay and instruction following with improved nuance and depth. The model is released under the Apache‑2.0 license.
Good at
- Roleplay and instruction following
- High‑precision FP32 remastering
- Improved perplexity over base models
Limits
- No vision support
- Requires 8 k context for memory estimates
- Large VRAM needed for higher quants
Best for
- Chatbots needing nuanced roleplay
- Instruction‑driven applications
- Research on FP32 remastering effects
Who it’s for. Developers and researchers who need a high‑quality Llama model with improved precision and roleplay capabilities. The model is suitable for applications that can accommodate its memory requirements.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 7.4 GB | 13.1 GB | Too big | Get file → | |
| Q3_K_S | 8.7 GB | 14.4 GB | Too big | Get file → | |
| Q3_K_M | 9.7 GB | 15.4 GB | Too big | Get file → | |
| Q3_K_L | 10.6 GB | 16.3 GB | Too big | Get file → | |
| IQ4_XS | 10.7 GB | 16.5 GB | Too big | Get file → | |
| IQ4_NL | 11.4 GB | 17.1 GB | Too big | Get file → | |
| Q4_K_M | 12.0 GB | 17.7 GB | Too big | Get file → | |
| Q5_K_S | 13.8 GB | 19.5 GB | Too big | Get file → | |
| Q5_K_M | 14.2 GB | 19.9 GB | Too big | Get file → | |
| Q6_K | 16.4 GB | 22.1 GB | Too big | Get file → | |
| Q8_0 | 21.2 GB | 26.9 GB | Too big | Get file → |
For 8 GB VRAM use Q2_K (file size 7.42 GB, estimated 18.3 GB memory at 8 k context). For 12 GB VRAM use Q4_K_M (12.04 GB, 22.9 GB memory). For 16 GB VRAM use Q5_K_M (14.16 GB, 25.1 GB memory). Memory estimates are approximate.
What GPU do you need for Psyonic Cetacean Ultra Quality 20b?
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 Q4_K_M (12.0 GB file, about 22.9 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (16.4 GB file, about 27.3 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (21.2 GB file, about 32.1 GB in use).
Which Psyonic Cetacean Ultra Quality 20b quant should you choose?
Q4_K_M is the usual starting point for Psyonic Cetacean Ultra Quality 20b: it balances file size and quality well. Here it is a 12.0 GB file.
The Q8_0 file is 21.2 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is Q2_K at 7.4 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 Psyonic Cetacean Ultra Quality 20b
How much VRAM does Psyonic Cetacean Ultra Quality 20b need?
About 22.9 GB at Q4_K_M with an 8K context window. That is the 12.0 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 Psyonic Cetacean Ultra Quality 20b on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 18.3 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Psyonic Cetacean Ultra Quality 20b GGUF?
It depends on the quant: Q2_K is 7.4 GB, Q3_K_S is 8.7 GB, Q3_K_M is 9.7 GB, Q3_K_L is 10.6 GB, IQ4_XS is 10.7 GB, IQ4_NL is 11.4 GB and 5 more.
What context length does Psyonic Cetacean Ultra Quality 20b support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 10.4 GB at 8K and 5.2 GB at 4K.
Where can I download Psyonic Cetacean Ultra Quality 20b GGUF?
The files are on Hugging Face in the DavidAU/Psyonic-Cetacean-Ultra-Quality-20b-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Psyonic Cetacean Ultra Quality 20b 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.
Can I run Psyonic Cetacean Ultra Quality 20b on 8 GB VRAM?
Use the Q2_K quant, which requires about 18.3 GB memory at 8 k context, so 8 GB VRAM is insufficient.
Does this model support vision tasks?
No, the model has no vision capabilities.
What license applies to this model?
The model is released under the Apache‑2.0 license.