OR

Orca 2 13B

OrcaGGUF by TheBlokeUpdated 2023-11-21
Download on Hugging Face
Parameters13B
Context4K
Layers40
Architecturellama
Smallest quant5.4 GB
Quick answer

Orca 2 13B 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).

Orca 2 13B – a research‑focused reasoning model in GGUF format

Orca 2 13B is a finetuned version of LLaMA‑2, optimized for reasoning tasks such as math, reading comprehension, and text summarization. It is released for research purposes only and is not trained with RLHF or DPO. The model is available in multiple GGUF quantisations for CPU and GPU inference.

Good at

  • Reasoning over user‑provided data
  • Math problem solving
  • Text summarization

Limits

  • Not optimized for chat
  • No vision support
  • Requires 8‑k context for full performance

Best for

  • Research on reasoning capabilities
  • Fine‑tuning for specific tasks
  • Evaluating synthetic training data

Who it’s for. Researchers and developers who need a large language model focused on reasoning and who are willing to fine‑tune it for chat or specific applications. The model is not intended for production chat use without further optimisation.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K5.4 GB 9.3 GB
Too big Get file →
Q3_K_S5.7 GB 9.5 GB
Too big Get file →
Q3_K_M6.3 GB 10.2 GB
Too big Get file →
Q3_K_L6.9 GB 10.8 GB
Too big Get file →
Q4_07.4 GB 11.2 GB
Too big Get file →
Q4_K_S7.4 GB 11.3 GB
Too big Get file →
Q4_K_M7.9 GB 11.7 GB
Too big Get file →
Q5_09.0 GB 12.8 GB
Too big Get file →
Q5_K_S9.0 GB 12.8 GB
Too big Get file →
Q5_K_M9.2 GB 13.1 GB
Too big Get file →
Q6_K10.7 GB 14.5 GB
Too big Get file →
Q8_013.8 GB 17.7 GB
Too big Get file →

For 8 GB VRAM use Q4_K_M (7.87 GB file, ~15.1 GB VRAM at 8k context). For 12 GB VRAM use Q5_K_M (9.23 GB file, ~16.4 GB VRAM). For 16 GB VRAM use Q6_K (10.68 GB file, ~17.9 GB VRAM). Estimates are approximate.

What GPU do you need for Orca 2 13B?

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 Orca 2 13B quant should you choose?

Q4_K_M is the usual starting point for Orca 2 13B: 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 context4,096 tokens
KV cache (fp16)800 KB per token

Source

Quantized byTheBloke
FamilyOrca
Licenseother
Downloads (HF)2,601
Last updated2023-11-21

Frequently asked questions about Orca 2 13B

How much VRAM does Orca 2 13B 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 Orca 2 13B 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 Orca 2 13B 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 Orca 2 13B support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 6.7 GB at 8K and 3.4 GB at 4K.

Where can I download Orca 2 13B GGUF?

The files are on Hugging Face in the TheBloke/Orca-2-13B-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 Orca 2 13B 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 Orca 2 13B on 8 GB VRAM?

Use the Q4_K_M quantised model; it requires about 15.1 GB VRAM at 8k context, so 8 GB VRAM is insufficient.

Does Orca 2 13B support vision tasks?

No, the model has no vision capabilities.

Is Orca 2 13B suitable for chat applications out of the box?

No, it is not optimised for chat and lacks RLHF or DPO training.

Other GGUFs of Orca-2-13b

Similar models

Browse all →

More from TheBloke

All by TheBloke →

More Orca models

All Orca →

Other medium models

All medium models →