QW

qwenv2 7b inst imatrix

QwenGGUF by nistenUpdated 2024-06-16
Download on Hugging Face
Parameters7.62B
Context32K
Layers28
Architectureqwen2
Smallest quant4.2 GB
Quick answer

qwenv2 7b inst imatrix needs about 5.8 GB of memory at its main file (a 4.8 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 8 quants, from 4.2 GB to 15.2 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.9 GB.

qwenv2 7b inst imatrix is a 7.62B-parameter Qwen model in GGUF format, quantized by nisten. Its trained context length is 32K tokens. The repository has 8 quant files, from 4.2 GB to 15.2 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—4.2 GB 5.2 GB
Fits Get file →
—4.4 GB 5.3 GB
Fits Get file →
—4.6 GB 5.6 GB
Fits Get file →
—4.8 GB 5.8 GB
Fits Get file →
—5.6 GB 6.5 GB
Fits Get file →
—6.1 GB 7.1 GB
Fits Get file →
—8.1 GB 9.1 GB
Too big Get file →
BF1615.2 GB 16.2 GB
Too big Get file →

What GPU do you need for qwenv2 7b inst imatrix?

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 the main file (4.8 GB file, about 5.8 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (6.1 GB file, about 7.1 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (8.1 GB file, about 9.1 GB in use).
  • 16 GB VRAM: the best quant that fits is the main file (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 qwenv2 7b inst imatrix quant should you choose?

If memory is tight, the smallest file is the first one in the table at 4.2 GB, with the quality trade-offs that come with fewer bits.

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 bynisten
FamilyQwen
Licenseapache-2.0
Downloads (HF)318
Last updated2024-06-16

Frequently asked questions about qwenv2 7b inst imatrix

How much VRAM does qwenv2 7b inst imatrix need?

About 5.8 GB at its main file with an 8K context window. That is the 4.8 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 qwenv2 7b inst imatrix on an 8 GB GPU?

Yes, with the smaller files: the 6.1 GB file needs about 7.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of qwenv2 7b inst imatrix GGUF?

It depends on the quant: file is 4.2 GB, file is 4.4 GB, file is 4.6 GB, file is 4.8 GB, file is 5.6 GB, file is 6.1 GB and 2 more.

What context length does qwenv2 7b inst imatrix 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 qwenv2 7b inst imatrix GGUF?

The files are on Hugging Face in the nisten/qwenv2-7b-inst-imatrix-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 qwenv2 7b inst imatrix use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Other GGUFs of Qwen2-7B-Instruct

Similar models

Browse all →

More from nisten

All by nisten →

More Qwen models

All Qwen →

Other small models

All small models →