LL

nousresearch_yarn-llama-2-70b-32k

LlamaGGUF by TheBlokeUpdated 2023-11-20
Download on Hugging Face
Parameters69B
Context32K
Layers80
Architecturellama
Smallest quant29.3 GB
Quick answer

nousresearch_yarn-llama-2-70b-32k needs about 44.6 GB of memory at Q4_K_M (a 41.4 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 10 quants, from 29.3 GB (Q2_K) to 48.8 GB (Q5_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.

NousResearch Yarn‑Llama‑2‑70B‑32K – large‑context language model

NousResearch Yarn‑Llama‑2‑70B‑32K is a 69‑billion‑parameter Llama‑family model trained for a 32k token context window. It is available in GGUF format and supports long‑context generation. The model is released under the apache‑2.0 license.

Good at

  • Long‑context text generation
  • High‑parameter language understanding
  • Large token windows

Limits

  • No vision support
  • Requires GPU for efficient inference
  • Large VRAM needed for higher‑quality quants

Best for

  • Research on long‑form content
  • Chatbots needing extended context
  • Data analysis with long sequences

Who it’s for. Developers and researchers who need a high‑capacity language model with a 32k token context. Suitable for local inference on systems with sufficient GPU memory.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K29.3 GB 32.5 GB
Too big Get file →
Q3_K_S29.9 GB 33.1 GB
Too big Get file →
Q3_K_M33.2 GB 36.4 GB
Too big Get file →
Q3_K_L36.1 GB 39.3 GB
Too big Get file →
Q4_038.9 GB 42.1 GB
Too big Get file →
Q4_K_S39.1 GB 42.3 GB
Too big Get file →
Q4_K_M41.4 GB 44.6 GB
Too big Get file →
Q5_047.5 GB 50.6 GB
Too big Get file →
Q5_K_S47.5 GB 50.6 GB
Too big Get file →
Q5_K_M48.8 GB 51.9 GB
Too big Get file →

For 8 GB VRAM use Q2_K or Q3_K_S (file sizes 29.28 GB and 29.92 GB). For 12 GB VRAM Q4_K_S (39.07 GB) is suitable. For 16 GB VRAM Q4_K_M (41.42 GB) offers a balance of size and quality. Estimates are approximate.

What GPU do you need for nousresearch_yarn-llama-2-70b-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: no quant fits at an 8K context.
  • 24 GB VRAM: no quant fits at an 8K context.
  • 32 GB VRAM: no quant fits at an 8K context.
  • 48 GB VRAM: the best quant that fits is Q4_K_M (41.4 GB file, about 44.6 GB in use).

Which nousresearch_yarn-llama-2-70b-32k quant should you choose?

Q4_K_M is the usual starting point for nousresearch_yarn-llama-2-70b-32k: it balances file size and quality well. Here it is a 41.4 GB file.

If memory is tight, the smallest file is Q2_K at 29.3 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
Parameters69B
Layers80
Trained context32,768 tokens
KV cache (fp16)320 KB per token

Source

Quantized byTheBloke
FamilyLlama
Licenseapache-2.0
Downloads (HF)1,974
Last updated2023-11-20

Frequently asked questions about nousresearch_yarn-llama-2-70b-32k

How much VRAM does nousresearch_yarn-llama-2-70b-32k need?

About 44.6 GB at Q4_K_M with an 8K context window. That is the 41.4 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-2-70b-32k on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 32.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of nousresearch_yarn-llama-2-70b-32k GGUF?

It depends on the quant: Q2_K is 29.3 GB, Q3_K_S is 29.9 GB, Q3_K_M is 33.2 GB, Q3_K_L is 36.1 GB, Q4_0 is 38.9 GB, Q4_K_S is 39.1 GB and 4 more.

What context length does nousresearch_yarn-llama-2-70b-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 2.7 GB at 8K and 10.7 GB at 32K.

Where can I download nousresearch_yarn-llama-2-70b-32k GGUF?

The files are on Hugging Face in the TheBloke/Yarn-Llama-2-70B-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 nousresearch_yarn-llama-2-70b-32k use?

Hugging Face lists the license as apache-2.0. 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?

Use the Q2_K or Q3_K_S quantised files; they fit within 8 GB VRAM with approximate memory usage of 32.5 GB and 33.1 GB respectively.

Does this model support vision tasks?

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

What license applies to this model?

The model is released under the apache‑2.0 license.

Similar models

Browse all →

More from TheBloke

All by TheBloke →

More Llama models

All Llama →

Other large models

All large models →