NousResearch Yarn Llama 2 70b 32k iMat needs about 17.7 GB of memory at IQ1_S (a 14.5 GB file) with an 8K context window, so it fits on a 24 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.
NousResearch Yarn Llama 2 70b 32k iMat is a 69B-parameter Llama model in GGUF format, quantized by NexesQuants. Its trained context length is 32K tokens. The repository has 1 quant file, from 14.5 GB (IQ1_S) to 14.5 GB (IQ1_S).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 14.5 GB | 17.7 GB | Too big | Get file → |
What GPU do you need for NousResearch Yarn Llama 2 70b 32k iMat?
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: the best quant that fits is IQ1_S (14.5 GB file, about 17.7 GB in use).
Which NousResearch Yarn Llama 2 70b 32k iMat quant should you choose?
IQ1_S (14.5 GB) is the middle option in this repository. 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
Frequently asked questions about NousResearch Yarn Llama 2 70b 32k iMat
How much VRAM does NousResearch Yarn Llama 2 70b 32k iMat need?
About 17.7 GB at IQ1_S with an 8K context window. That is the 14.5 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 iMat on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 17.7 GB, so you would need a larger GPU or CPU offloading.
What is the file size of NousResearch Yarn Llama 2 70b 32k iMat GGUF?
It depends on the quant: IQ1_S is 14.5 GB.
What context length does NousResearch Yarn Llama 2 70b 32k iMat 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 iMat GGUF?
The files are on Hugging Face in the NexesQuants/NousResearch_Yarn-Llama-2-70b-32k-iMat.GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.