LL

nousresearch_yarn-llama-2-13b-128k

LlamaGGUF by TheBlokeUpdated 2023-09-27
Download on Hugging Face
Parameters13B
Context128K
Layers40
Architecturellama
Smallest quant5.4 GB
Quick answer

nousresearch_yarn-llama-2-13b-128k 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.

Nous-Yarn-Llama-2-13B-128K: 13B Llama model with 128k token context

Nous-Yarn-Llama-2-13B-128K is a 13‑billion‑parameter Llama model optimized for long‑context usage. It supports up to 128,000 tokens and requires Flash Attention 2 for correct operation. The model is available in GGUF format for llama.cpp and compatible clients.

Good at

  • Long‑context text generation
  • Large‑scale document summarisation
  • Complex reasoning over extended prompts

Limits

  • Requires Flash Attention 2 library
  • No vision or multimodal support
  • License is llama2

Best for

  • Chatbots needing extended memory
  • Research on long‑form content
  • Story generation with large context

Who it’s for. Developers and researchers who need a Llama‑based model capable of handling very long prompts and contexts. The model is suitable for local inference using 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 (7.37 GB file, ~14.6 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 nousresearch_yarn-llama-2-13b-128k?

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 nousresearch_yarn-llama-2-13b-128k quant should you choose?

Q4_K_M is the usual starting point for nousresearch_yarn-llama-2-13b-128k: 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 context131,072 tokens
KV cache (fp16)800 KB per token

Source

Quantized byTheBloke
FamilyLlama
Licensellama2
Downloads (HF)5,221
Last updated2023-09-27

Frequently asked questions about nousresearch_yarn-llama-2-13b-128k

How much VRAM does nousresearch_yarn-llama-2-13b-128k 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 nousresearch_yarn-llama-2-13b-128k 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 nousresearch_yarn-llama-2-13b-128k 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 nousresearch_yarn-llama-2-13b-128k support?

The GGUF header lists a trained context length of 131,072 tokens (128K). 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 nousresearch_yarn-llama-2-13b-128k GGUF?

The files are on Hugging Face in the TheBloke/Yarn-Llama-2-13B-128K-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 nousresearch_yarn-llama-2-13b-128k use?

Hugging Face lists the license as llama2. 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?

Yes, using the Q4_K quantisation which requires about 14.6 GB VRAM at 8k context, which is close to 8 GB but may need CPU fallback.

Does this model support image input?

No, it is a text‑only language model with no vision capabilities.

What library is needed for inference?

Flash Attention 2 is required for correct operation; install via the model usage instructions.

Similar models

Browse all →

More from TheBloke

All by TheBloke →

More Llama models

All Llama →

Other medium models

All medium models →