QW

Qwen1.5-7B-Chat

QwenGGUF by ZeroWwUpdated 2024-06-23
Download on Hugging Face
Parameters7.72B
Context32K
Layers32
Architectureqwen2
Smallest quant7.1 GB
Quick answer

Qwen1.5-7B-Chat needs about 12.6 GB of memory at Q6_K (a 7.8 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 4 quants, from 7.1 GB (Q5_K) to 15.4 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 17.2 GB.

Qwen1.5-7B-Chat is a 7.72B-parameter Qwen model in GGUF format, quantized by ZeroWw. Its trained context length is 32K tokens. The repository has 4 quant files, from 7.1 GB (Q5_K) to 15.4 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K7.1 GB 11.9 GB
Too big Get file →
Q6_K7.8 GB 12.6 GB
Too big Get file →
Q8_09.4 GB 14.2 GB
Too big Get file →
F1615.4 GB 20.2 GB
Too big Get file →

What GPU do you need for Qwen1.5-7B-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: the best quant that fits is Q5_K (7.1 GB file, about 11.9 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (9.4 GB file, about 14.2 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (15.4 GB file, about 20.2 GB in use).

Which Qwen1.5-7B-Chat quant should you choose?

Q6_K (7.8 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.

If memory is tight, the smallest file is Q5_K at 7.1 GB, with the quality trade-offs that come with fewer bits. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen2
Parameters7.72B
Layers32
Trained context32,768 tokens
KV cache (fp16)512 KB per token

Source

Quantized byZeroWw
FamilyQwen
Licensemit
Downloads (HF)41
Last updated2024-06-23

Frequently asked questions about Qwen1.5-7B-Chat

How much VRAM does Qwen1.5-7B-Chat need?

About 12.6 GB at Q6_K with an 8K context window. That is the 7.8 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 Qwen1.5-7B-Chat on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 11.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Qwen1.5-7B-Chat GGUF?

It depends on the quant: Q5_K is 7.1 GB, Q6_K is 7.8 GB, Q8_0 is 9.4 GB, F16 is 15.4 GB.

What context length does Qwen1.5-7B-Chat support?

The GGUF header lists a trained context length of 32,768 tokens (32K). 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 Qwen1.5-7B-Chat GGUF?

The files are on Hugging Face in the ZeroWw/Qwen1.5-7B-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 Qwen1.5-7B-Chat use?

Hugging Face lists the license as mit. 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 ZeroWw

All by ZeroWw →

More Qwen models

All Qwen →

Other small models

All small models →