PS

Psyonic-Cetacean-full-precision

PsyonicGGUF by mradermacherUpdated 2024-12-16
Download on Hugging Face
Parameters20B
Context4K
Layers62
Architecturellama
Smallest quant4.4 GB
Quick answer

Psyonic-Cetacean-full-precision 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 21 quants, from 4.4 GB (IQ1_S) to 16.4 GB (Q6_K).

20B parameter Psyonic model in GGUF format

Psyonic-Cetacean-full-precision is a 20 billion parameter llama architecture model. It is available in multiple quantized GGUF files ranging from IQ1_S to Q6_K. The model supports a 4096 token context window and is released under the Apache‑2.0 license.

Good at

  • Large context reasoning
  • High‑quality text generation
  • Multilingual support

Limits

  • Requires 15–27 GB VRAM at 8 k context
  • No vision or audio capabilities
  • No mixture‑of‑experts features

Best for

  • Research prototypes needing high precision
  • Fine‑tuning on custom datasets
  • Deployments on high‑end GPUs

Who it’s for. Developers and researchers who need a large, high‑precision language model and have access to GPUs with sufficient VRAM. The model is suitable for tasks that demand detailed text generation and long‑context understanding.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S4.4 GB 10.1 GB
Too big Get file →
IQ1_M4.8 GB 10.5 GB
Too big Get file →
IQ2_XXS5.4 GB 11.1 GB
Too big Get file →
IQ2_XS5.9 GB 11.6 GB
Too big Get file →
IQ2_S6.4 GB 12.1 GB
Too big Get file →
IQ2_M6.9 GB 12.6 GB
Too big Get file →
Q2_K7.4 GB 13.1 GB
Too big Get file →
IQ3_XXS7.6 GB 13.3 GB
Too big Get file →
IQ3_XS8.2 GB 13.9 GB
Too big Get file →
IQ3_S8.7 GB 14.4 GB
Too big Get file →
Q3_K_S8.7 GB 14.4 GB
Too big Get file →
IQ3_M9.2 GB 14.9 GB
Too big Get file →
Q3_K_M9.7 GB 15.4 GB
Too big Get file →
Q3_K_L10.6 GB 16.3 GB
Too big Get file →
IQ4_XS10.7 GB 16.4 GB
Too big Get file →
Q4_011.3 GB 17.0 GB
Too big Get file →
Q4_K_S11.4 GB 17.1 GB
Too big Get file →
Q4_K_M12.0 GB 17.7 GB
Too big Get file →
Q5_K_S13.8 GB 19.5 GB
Too big Get file →
Q5_K_M14.2 GB 19.9 GB
Too big Get file →
Q6_K16.4 GB 22.1 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (4.39 GB, 15.3 GB VRAM). For 12 GB VRAM, IQ2_XS (5.94 GB, 16.8 GB VRAM) or Q2_K (7.42 GB, 18.3 GB VRAM). For 24 GB VRAM, Q5_K_M (14.16 GB, 25.1 GB VRAM) offers a good balance of size and performance. Estimates are approximate.

What GPU do you need for Psyonic-Cetacean-full-precision?

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 IQ1_M (4.8 GB file, about 15.7 GB in use).
  • 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).

Which Psyonic-Cetacean-full-precision quant should you choose?

Q4_K_M is the usual starting point for Psyonic-Cetacean-full-precision: it balances file size and quality well. Here it is a 12.0 GB file.

If memory is tight, the smallest file is IQ1_S at 4.4 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

Architecturellama
Parameters20B
Layers62
Trained context4,096 tokens
KV cache (fp16)1240 KB per token

Source

Quantized bymradermacher
FamilyPsyonic
Licenseapache-2.0
Downloads (HF)3,709
Last updated2024-12-16

Frequently asked questions about Psyonic-Cetacean-full-precision

How much VRAM does Psyonic-Cetacean-full-precision 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-full-precision on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 15.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Psyonic-Cetacean-full-precision GGUF?

It depends on the quant: IQ1_S is 4.4 GB, IQ1_M is 4.8 GB, IQ2_XXS is 5.4 GB, IQ2_XS is 5.9 GB, IQ2_S is 6.4 GB, IQ2_M is 6.9 GB and 15 more.

What context length does Psyonic-Cetacean-full-precision 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-full-precision GGUF?

The files are on Hugging Face in the mradermacher/Psyonic-Cetacean-full-precision-i1-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-full-precision 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 this model on 8 GB VRAM?

Use the IQ1_S quant, which is 4.39 GB and requires about 15.3 GB VRAM at 8 k context.

Does the model support vision or audio?

No, the model has no vision or audio capabilities.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Psyonic models

All Psyonic →

Other medium models

All medium models →