PA

Palmyra Creative

PalmyraGGUF by mradermacherUpdated 2026-08-27
Download on Hugging Face
Parameters122B
Context128K
Layers140
Architecturellama
Smallest quant0.0 GB
Quick answer

Palmyra Creative needs about 78.4 GB of memory at Q4_K_M (a 73.2 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 23 quants, from 0.0 GB to 86.2 GB (Q5_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 18.8 GB.

Palmyra Creative – a 122‑billion‑parameter creative writing model

Palmyra Creative is a 122‑billion‑parameter LLM fine‑tuned from Palmyra‑X‑004. It supports a 131,072‑token context window and is designed for creative writing tasks such as narrative, poetry, and marketing copy. The model is available in multiple GGUF quantizations.

Good at

  • Creative narrative generation
  • Poetry and scriptwriting
  • Marketing copy creation

Limits

  • Large VRAM requirement for high‑quality quants
  • No vision support
  • License is other

Best for

  • Writing fiction drafts
  • Generating marketing slogans
  • Creating dialogue for scripts

Who it’s for. The model is aimed at writers, content creators, and professionals who need high‑quality creative text. It is suitable for those who can allocate sufficient GPU memory to run the desired quantization.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 5.2 GB
Fits Get file →
IQ1_S26.0 GB 31.2 GB
Too big Get file →
IQ1_M28.5 GB 33.7 GB
Too big Get file →
IQ2_XXS32.6 GB 37.8 GB
Too big Get file →
IQ2_XS36.2 GB 41.4 GB
Too big Get file →
IQ2_S38.0 GB 43.2 GB
Too big Get file →
IQ2_M41.3 GB 46.5 GB
Too big Get file →
Q2_K_S41.7 GB 46.9 GB
Too big Get file →
Q2_K45.1 GB 50.3 GB
Too big Get file →
IQ3_XXS47.0 GB 52.2 GB
Too big Get file →
IQ3_XS50.2 GB 55.3 GB
Too big Get file →
Q3_K_S52.8 GB 58.0 GB
Too big Get file →
IQ3_S53.0 GB 58.2 GB
Too big Get file →
IQ3_M54.7 GB 59.9 GB
Too big Get file →
Q3_K_M58.8 GB 64.0 GB
Too big Get file →
Q3_K_L64.0 GB 69.2 GB
Too big Get file →
IQ4_XS65.3 GB 70.5 GB
Too big Get file →
Q4_069.1 GB 74.3 GB
Too big Get file →
Q4_K_S69.4 GB 74.6 GB
Too big Get file →
Q4_K_M73.2 GB 78.4 GB
Too big Get file →
Q4_176.4 GB 81.6 GB
Too big Get file →
Q5_K_S84.0 GB 89.2 GB
Too big Get file →
Q5_K_M86.2 GB 91.4 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (26.03 GB file, 31.2 GB memory at 8k context). For 16 GB VRAM, IQ1_M (28.5 GB file, 33.7 GB memory) or IQ2_XXS (32.61 GB file, 37.8 GB memory). For 32 GB VRAM, Q4_K_M (73.24 GB file, 78.4 GB memory) or Q5_K_M (86.22 GB file, 91.4 GB memory). Memory estimates are approximate.

What GPU do you need for Palmyra Creative?

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: the best quant that fits is the main file (0.0 GB file, about 5.2 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 5.2 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 5.2 GB in use).
  • 16 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 5.2 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 5.2 GB in use).
  • 32 GB VRAM: the best quant that fits is IQ1_S (26.0 GB file, about 31.2 GB in use).
  • 48 GB VRAM: the best quant that fits is Q2_K_S (41.7 GB file, about 46.9 GB in use).

Which Palmyra Creative quant should you choose?

Q4_K_M is the usual starting point for Palmyra Creative: it balances file size and quality well. Here it is a 73.2 GB file.

If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters122B
Layers140
Trained context131,072 tokens
KV cache (fp16)560 KB per token

Source

Quantized bymradermacher
FamilyPalmyra
Licenseother
Downloads (HF)595
Last updated2026-08-27

Frequently asked questions about Palmyra Creative

How much VRAM does Palmyra Creative need?

About 78.4 GB at Q4_K_M with an 8K context window. That is the 73.2 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 Palmyra Creative on an 8 GB GPU?

Yes, with the smaller files: the 0.0 GB file needs about 5.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Palmyra Creative GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 26.0 GB, IQ1_M is 28.5 GB, IQ2_XXS is 32.6 GB, IQ2_XS is 36.2 GB, IQ2_S is 38.0 GB and 17 more.

What context length does Palmyra Creative support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 4.7 GB at 8K and 18.8 GB at 32K.

Where can I download Palmyra Creative GGUF?

The files are on Hugging Face in the mradermacher/Palmyra-Creative-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 Palmyra Creative use?

Hugging Face lists the license as other. 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 Palmyra Creative on 8 GB VRAM?

Use the IQ1_S quant, which requires about 31.2 GB of VRAM at 8k context. It is the smallest quant that supports the full model.

Does Palmyra Creative support image inputs?

No, the model has no vision capabilities.

What license applies to Palmyra Creative?

The model is released under an "other" license, not a standard open‑source license.

Other GGUFs of Palmyra-Creative

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Palmyra models

All Palmyra →

Other large models

All large models →