LL

nousresearch_yarn-llama-2-7b-128k

LlamaGGUF by TheBlokeUpdated 2023-09-27
Download on Hugging Face
Parameters6.74B
Context128K
Layers32
Architecturellama
Smallest quant2.8 GB
Quick answer

nousresearch_yarn-llama-2-7b-128k needs about 8.9 GB of memory at Q4_K_M (a 4.1 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 12 quants, from 2.8 GB (Q2_K) to 7.2 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 17.2 GB.

NousResearch Yarn Llama 2 7B 128K – long‑context LLM in GGUF format

NousResearch Yarn Llama 2 7B 128K is a 6.74B parameter model trained for up to 131072 tokens of context. It is available in GGUF format and can be run with llama.cpp or compatible libraries. The model is licensed under llama2.

Good at

  • Long‑context generation
  • High token throughput
  • Versatile prompt handling

Limits

  • No vision support
  • Requires Flash Attention for optimal performance
  • No explicit instruction tuning

Best for

  • Chat applications needing long context
  • Story generation with extended memory
  • Research prototyping on local hardware

Who it’s for. Developers and researchers who need a 7B LLM that can handle 128k token contexts on local machines. The model is suitable for projects that can install Flash Attention and use llama.cpp or compatible GUIs.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K2.8 GB 7.6 GB
Tight Get file →
Q3_K_S2.9 GB 7.7 GB
Tight Get file →
Q3_K_M3.3 GB 8.1 GB
Too big Get file →
Q3_K_L3.6 GB 8.4 GB
Too big Get file →
Q4_03.8 GB 8.6 GB
Too big Get file →
Q4_K_S3.9 GB 8.7 GB
Too big Get file →
Q4_K_M4.1 GB 8.9 GB
Too big Get file →
Q5_04.7 GB 9.4 GB
Too big Get file →
Q5_K_S4.7 GB 9.4 GB
Too big Get file →
Q5_K_M4.8 GB 9.6 GB
Too big Get file →
Q6_K5.5 GB 10.3 GB
Too big Get file →
Q8_07.2 GB 12.0 GB
Too big Get file →

For 8 GB VRAM, use Q4_K or Q4_K_S (file size 3.83 GB or 3.86 GB, memory ~8.6–8.7 GB). For 12 GB VRAM, Q5_K_M (file size 4.78 GB, memory ~9.6 GB) or Q6_K (file size 5.53 GB, memory ~10.3 GB) are suitable. For 16 GB VRAM, Q8_0 (file size 7.16 GB, memory ~12 GB) provides the highest quality.

What GPU do you need for nousresearch_yarn-llama-2-7b-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: the best quant that fits is Q3_K_S (2.9 GB file, about 7.7 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (7.2 GB file, about 12.0 GB in use).

Which nousresearch_yarn-llama-2-7b-128k quant should you choose?

Q4_K_M is the usual starting point for nousresearch_yarn-llama-2-7b-128k: it balances file size and quality well. Here it is a 4.1 GB file.

The Q8_0 file is 7.2 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 2.8 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
Parameters6.74B
Layers32
Trained context131,072 tokens
KV cache (fp16)512 KB per token

Source

Quantized byTheBloke
FamilyLlama
Licensellama2
Downloads (HF)1,179
Last updated2023-09-27

Frequently asked questions about nousresearch_yarn-llama-2-7b-128k

How much VRAM does nousresearch_yarn-llama-2-7b-128k need?

About 8.9 GB at Q4_K_M with an 8K context window. That is the 4.1 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-2-7b-128k on an 8 GB GPU?

Yes, with Q3_K_S: the 2.9 GB file needs about 7.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of nousresearch_yarn-llama-2-7b-128k GGUF?

It depends on the quant: Q2_K is 2.8 GB, Q3_K_S is 2.9 GB, Q3_K_M is 3.3 GB, Q3_K_L is 3.6 GB, Q4_0 is 3.8 GB, Q4_K_S is 3.9 GB and 6 more.

What context length does nousresearch_yarn-llama-2-7b-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 4.3 GB at 8K and 17.2 GB at 32K.

Where can I download nousresearch_yarn-llama-2-7b-128k GGUF?

The files are on Hugging Face in the TheBloke/Yarn-Llama-2-7B-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-2-7b-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 Q4_K or Q4_K_S quantisations, which require approximately 8.6–8.7 GB of VRAM at 8k context.

Does this model support image inputs?

No, the model does not have vision capabilities.

What libraries can I use to run this model?

Supported clients include llama.cpp, text-generation-webui, LM Studio, and llama-cpp-python, among others.

Similar models

Browse all →

More from TheBloke

All by TheBloke →

More Llama models

All Llama →

Other small models

All small models →