RO

TheDrummer/Rocinante-12B-v1.1

RocinanteGGUF by featherless-ai-quantsUpdated 2024-11-10
Download on Hugging Face
Parameters12.2B
Context1000K
Layers40
Architecturellama
Smallest quant4.8 GB
Quick answer

TheDrummer/Rocinante-12B-v1.1 needs about 9.3 GB of memory at Q4_K_M (a 7.5 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 11 quants, from 4.8 GB (Q2_K) to 13.0 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

Rocinante 12B v1.1 – a versatile 12.2B Llama model

TheDrummer/Rocinante-12B-v1.1 is a 12.2B parameter Llama model trained on 1,024,000 context tokens. It offers rich prose and creative storytelling. The model is available in multiple GGUF quantizations for different memory budgets.

Good at

  • Creative storytelling
  • Rich prose generation
  • Adventure‑focused dialogue

Limits

  • No vision support
  • License type is other
  • Large context length may require more memory

Best for

  • Writing adventure narratives
  • Generating creative content
  • Chatting with story prompts

Who it’s for. Developers and writers who need a large language model for creative writing and storytelling. The model is suitable for users with access to a GPU that can handle the chosen quantization.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K4.8 GB 6.6 GB
Fits Get file →
Q3_K_S5.5 GB 7.4 GB
Tight Get file →
Q3_K_M6.1 GB 7.9 GB
Tight Get file →
Q3_K_L6.6 GB 8.4 GB
Too big Get file →
IQ4_XS6.8 GB 8.6 GB
Too big Get file →
Q4_K_S7.1 GB 9.0 GB
Too big Get file →
Q4_K_M7.5 GB 9.3 GB
Too big Get file →
Q5_K_S8.5 GB 10.4 GB
Too big Get file →
Q5_K_M8.7 GB 10.6 GB
Too big Get file →
Q6_K10.1 GB 11.9 GB
Too big Get file →
Q8_013.0 GB 14.9 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (est. 9.3 GB) or Q4_K_S (est. 9 GB). For 12 GB VRAM, Q5_K_M (est. 10.6 GB) or Q6_K (est. 11.9 GB) are suitable. Larger models like Q8_0 require 14.9 GB memory and 13.02 GB file size.

What GPU do you need for TheDrummer/Rocinante-12B-v1.1?

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: the best quant that fits is Q3_K_M (6.1 GB file, about 7.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (10.1 GB file, about 11.9 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (13.0 GB file, about 14.9 GB in use).

Which TheDrummer/Rocinante-12B-v1.1 quant should you choose?

Q4_K_M is the usual starting point for TheDrummer/Rocinante-12B-v1.1: it balances file size and quality well. Here it is a 7.5 GB file.

The Q8_0 file is 13.0 GB, about 1.7 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 4.8 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
Parameters12.2B
Layers40
Trained context1,024,000 tokens
KV cache (fp16)160 KB per token

Source

FamilyRocinante
Licenseother
Downloads (HF)885
Last updated2024-11-10

Frequently asked questions about TheDrummer/Rocinante-12B-v1.1

How much VRAM does TheDrummer/Rocinante-12B-v1.1 need?

About 9.3 GB at Q4_K_M with an 8K context window. That is the 7.5 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 TheDrummer/Rocinante-12B-v1.1 on an 8 GB GPU?

Yes, with Q3_K_M: the 6.1 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of TheDrummer/Rocinante-12B-v1.1 GGUF?

It depends on the quant: Q2_K is 4.8 GB, Q3_K_S is 5.5 GB, Q3_K_M is 6.1 GB, Q3_K_L is 6.6 GB, IQ4_XS is 6.8 GB, Q4_K_S is 7.1 GB and 5 more.

What context length does TheDrummer/Rocinante-12B-v1.1 support?

The GGUF header lists a trained context length of 1,024,000 tokens (1000K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.

Where can I download TheDrummer/Rocinante-12B-v1.1 GGUF?

The files are on Hugging Face in the featherless-ai-quants/TheDrummer-Rocinante-12B-v1.1-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 TheDrummer/Rocinante-12B-v1.1 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 Rocinante 12B v1.1 on 8 GB VRAM?

Yes, using Q4_K_M or Q4_K_S quantizations, which estimate 9.3 GB and 9 GB memory usage respectively.

What is the context length of this model?

The model was trained on 1,024,000 context tokens.

Does this model support vision?

No, the model does not have vision capabilities.

Other GGUFs of Rocinante-12B-v1.1

Similar models

Browse all →

More from featherless-ai-quants

All by featherless-ai-quants →

More Rocinante models

All Rocinante →

Other medium models

All medium models →