XU

XuanYuan2 70B Chat

XuanyuanGGUF by mradermacherUpdated 2024-11-08
Download on Hugging Face
Parameters69.1B
Context16K
Layers80
Architecturellama
Smallest quant25.5 GB
Quick answer

XuanYuan2 70B Chat needs about 44.7 GB of memory at Q4_K_M (a 41.5 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 9 quants, from 25.5 GB (Q2_K) to 48.8 GB (Q5_K_M).

XuanYuan2 70B Chat is a 69.1B-parameter Xuanyuan model in GGUF format, quantized by mradermacher. Its trained context length is 16K tokens. The repository has 9 quant files, from 25.5 GB (Q2_K) to 48.8 GB (Q5_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K25.5 GB 28.7 GB
Too big Get file →
Q3_K_S30.0 GB 33.2 GB
Too big Get file →
Q3_K_M33.4 GB 36.5 GB
Too big Get file →
Q3_K_L36.2 GB 39.4 GB
Too big Get file →
IQ4_XS37.3 GB 40.5 GB
Too big Get file →
Q4_K_S39.3 GB 42.5 GB
Too big Get file →
Q4_K_M41.5 GB 44.7 GB
Too big Get file →
Q5_K_S47.6 GB 50.7 GB
Too big Get file →
Q5_K_M48.8 GB 52.0 GB
Too big Get file →

What GPU do you need for XuanYuan2 70B Chat?

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: the best quant that fits is Q2_K (25.5 GB file, about 28.7 GB in use).
  • 48 GB VRAM: the best quant that fits is Q4_K_M (41.5 GB file, about 44.7 GB in use).

Which XuanYuan2 70B Chat quant should you choose?

Q4_K_M is the usual starting point for XuanYuan2 70B Chat: it balances file size and quality well. Here it is a 41.5 GB file.

If memory is tight, the smallest file is Q2_K at 25.5 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
Parameters69.1B
Layers80
Trained context16,384 tokens
KV cache (fp16)320 KB per token

Source

Quantized bymradermacher
FamilyXuanyuan
Licensellama2
Downloads (HF)61
Last updated2024-11-08

Frequently asked questions about XuanYuan2 70B Chat

How much VRAM does XuanYuan2 70B Chat need?

About 44.7 GB at Q4_K_M with an 8K context window. That is the 41.5 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 XuanYuan2 70B Chat on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 28.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of XuanYuan2 70B Chat GGUF?

It depends on the quant: Q2_K is 25.5 GB, Q3_K_S is 30.0 GB, Q3_K_M is 33.4 GB, Q3_K_L is 36.2 GB, IQ4_XS is 37.3 GB, Q4_K_S is 39.3 GB and 3 more.

What context length does XuanYuan2 70B Chat support?

The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 2.7 GB at 8K and 5.4 GB at 16K.

Where can I download XuanYuan2 70B Chat GGUF?

The files are on Hugging Face in the mradermacher/XuanYuan2-70B-Chat-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 XuanYuan2 70B Chat 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.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Xuanyuan models

All Xuanyuan →

Other large models

All large models →