LL

Qwen2.5 7B Instruct

LlamaGGUF by daitavanUpdated 2024-11-30
Download on Hugging Face
Parameters7.62B
Context32K
Layers28
Architectureqwen2
Smallest quant4.7 GB
Quick answer

Qwen2.5 7B Instruct needs about 9.1 GB of memory at BF16 (a 8.1 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 3 quants, from 4.7 GB (BF16) to 15.2 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.9 GB.

Qwen2.5 7B Instruct is a 7.62B-parameter Llama model in GGUF format, quantized by daitavan. Its trained context length is 32K tokens. The repository has 3 quant files, from 4.7 GB (BF16) to 15.2 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
BF164.7 GB 5.7 GB
Fits Get file →
BF168.1 GB 9.1 GB
Too big Get file →
BF1615.2 GB 16.2 GB
Too big Get file →

What GPU do you need for Qwen2.5 7B Instruct?

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: the best quant that fits is BF16 (4.7 GB file, about 5.7 GB in use).
  • 8 GB VRAM: the best quant that fits is BF16 (4.7 GB file, about 5.7 GB in use).
  • 12 GB VRAM: the best quant that fits is BF16 (8.1 GB file, about 9.1 GB in use).
  • 16 GB VRAM: the best quant that fits is BF16 (8.1 GB file, about 9.1 GB in use).
  • 24 GB VRAM: the best quant that fits is BF16 (15.2 GB file, about 16.2 GB in use).

Which Qwen2.5 7B Instruct quant should you choose?

BF16 (8.1 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

If memory is tight, the smallest file is BF16 at 4.7 GB, with the quality trade-offs that come with fewer bits. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen2
Parameters7.62B
Layers28
Trained context32,768 tokens
KV cache (fp16)56 KB per token

Source

Quantized bydaitavan
FamilyLlama
Downloads (HF)23
Last updated2024-11-30

Frequently asked questions about Qwen2.5 7B Instruct

How much VRAM does Qwen2.5 7B Instruct need?

About 9.1 GB at BF16 with an 8K context window. That is the 8.1 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 Qwen2.5 7B Instruct on an 8 GB GPU?

Yes, with BF16: the 4.7 GB file needs about 5.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Qwen2.5 7B Instruct GGUF?

It depends on the quant: BF16 is 4.7 GB, BF16 is 8.1 GB, BF16 is 15.2 GB.

What context length does Qwen2.5 7B Instruct support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.5 GB at 8K and 1.9 GB at 32K.

Where can I download Qwen2.5 7B Instruct GGUF?

The files are on Hugging Face in the daitavan/Qwen2.5-7B-Instruct-finetune-llamafactory-bf16-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from daitavan

All by daitavan →

More Llama models

All Llama →

Other small models

All small models →