OR

ddh0_orcamaid-v3-13b-32k

OrcamaidGGUF by TheBlokeUpdated 2024-01-10
Download on Hugging Face
Parameters13B
Context32K
Layers40
Architecturellama
Smallest quant5.4 GB
Quick answer

ddh0_orcamaid-v3-13b-32k needs about 15.1 GB of memory at Q4_K_M (a 7.9 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 12 quants, from 5.4 GB (Q2_K) to 13.8 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 26.8 GB.

ddh0_orcamaid-v3-13b-32k – a 13B Llama model with 32K context

ddh0_orcamaid-v3-13b-32k is a 13B parameter Llama model with a native context length of 32768 tokens. It is a weighted gradient SLERP merge of Orca-2-13b and Noromaid-13b-v0.3, designed for role‑playing and human‑like dialogue. The model is distributed in GGUF format and supports multiple quantizations.

Good at

  • Human‑like role‑playing
  • Large context handling
  • Customizable Alpaca prompts

Limits

  • No vision support
  • License terms from Microsoft Research apply
  • Requires GPU for efficient inference

Best for

  • Interactive storytelling
  • Long‑form conversation
  • Custom prompt engineering

Who it’s for. Developers and researchers who need a large‑context Llama model for text‑only applications. The model is suitable for local deployment via llama.cpp or compatible GUIs.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K5.4 GB 12.6 GB
Too big Get file →
Q3_K_S5.7 GB 12.9 GB
Too big Get file →
Q3_K_M6.3 GB 13.5 GB
Too big Get file →
Q3_K_L6.9 GB 14.1 GB
Too big Get file →
Q4_07.4 GB 14.6 GB
Too big Get file →
Q4_K_S7.4 GB 14.6 GB
Too big Get file →
Q4_K_M7.9 GB 15.1 GB
Too big Get file →
Q5_09.0 GB 16.2 GB
Too big Get file →
Q5_K_S9.0 GB 16.2 GB
Too big Get file →
Q5_K_M9.2 GB 16.4 GB
Too big Get file →
Q6_K10.7 GB 17.9 GB
Too big Get file →
Q8_013.8 GB 21.0 GB
Too big Get file →

For 8 GB VRAM, use Q4_K (file size 7.37 GB, estimated 14.6 GB memory at 8 k context). For 12 GB VRAM, Q5_K_M (file size 9.23 GB, estimated 16.4 GB memory). For 16 GB VRAM, Q6_K (file size 10.68 GB, estimated 17.9 GB memory).

What GPU do you need for ddh0_orcamaid-v3-13b-32k?

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 Q4_K_M (7.9 GB file, about 15.1 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (13.8 GB file, about 21.0 GB in use).

Which ddh0_orcamaid-v3-13b-32k quant should you choose?

Q4_K_M is the usual starting point for ddh0_orcamaid-v3-13b-32k: it balances file size and quality well. Here it is a 7.9 GB file.

The Q8_0 file is 13.8 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 5.4 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
Parameters13B
Layers40
Trained context32,768 tokens
KV cache (fp16)800 KB per token

Source

Quantized byTheBloke
FamilyOrcamaid
Licenseother
Downloads (HF)829
Last updated2024-01-10

Frequently asked questions about ddh0_orcamaid-v3-13b-32k

How much VRAM does ddh0_orcamaid-v3-13b-32k need?

About 15.1 GB at Q4_K_M with an 8K context window. That is the 7.9 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 ddh0_orcamaid-v3-13b-32k on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 12.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of ddh0_orcamaid-v3-13b-32k GGUF?

It depends on the quant: Q2_K is 5.4 GB, Q3_K_S is 5.7 GB, Q3_K_M is 6.3 GB, Q3_K_L is 6.9 GB, Q4_0 is 7.4 GB, Q4_K_S is 7.4 GB and 6 more.

What context length does ddh0_orcamaid-v3-13b-32k support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 6.7 GB at 8K and 26.8 GB at 32K.

Where can I download ddh0_orcamaid-v3-13b-32k GGUF?

The files are on Hugging Face in the TheBloke/OrcaMaid-v3-13B-32k-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 ddh0_orcamaid-v3-13b-32k 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 ddh0_orcamaid-v3-13b-32k on 8 GB VRAM?

Use the Q4_K quantization; it requires about 14.6 GB memory at 8 k context, so 8 GB VRAM will not suffice for full inference.

Does the model support vision tasks?

No, the model is text‑only and has no vision capabilities.

What license applies to this model?

The model is subject to the Microsoft Research License due to inclusion of Orca-2-13b.

Similar models

Browse all →

More from TheBloke

All by TheBloke →

More Orcamaid models

All Orcamaid →

Other medium models

All medium models →