QW

Med Qwen2

QwenGGUF by Echelon-AIUpdated 2024-07-02
Download on Hugging Face
Parameters7.62B
Context32K
Layers28
Architectureqwen2
Smallest quant5.4 GB
Quick answer

Med Qwen2 needs about 9.1 GB of memory at Q8_0 (a 8.1 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 3 quants, from 5.4 GB (Q5_K_M) to 15.2 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.9 GB.

Med Qwen2 is a 7.62B-parameter Qwen model in GGUF format, quantized by Echelon-AI. Its trained context length is 32K tokens. The repository has 3 quant files, from 5.4 GB (Q5_K_M) to 15.2 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_M5.4 GB 6.4 GB
Fits Get file →
Q8_08.1 GB 9.1 GB
Too big Get file →
BF1615.2 GB 16.2 GB
Too big Get file →

What GPU do you need for Med Qwen2?

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: the best quant that fits is Q5_K_M (5.4 GB file, about 6.4 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (8.1 GB file, about 9.1 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (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 Med Qwen2 quant should you choose?

Q8_0 (8.1 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

If memory is tight, the smallest file is Q5_K_M at 5.4 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
Parameters7.62B
Layers28
Trained context32,768 tokens
KV cache (fp16)56 KB per token

Source

Quantized byEchelon-AI
FamilyQwen
Licenseapache-2.0
Downloads (HF)48
Last updated2024-07-02

Frequently asked questions about Med Qwen2

How much VRAM does Med Qwen2 need?

About 9.1 GB at Q8_0 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 Med Qwen2 on an 8 GB GPU?

Yes, with Q5_K_M: the 5.4 GB file needs about 6.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Med Qwen2 GGUF?

It depends on the quant: Q5_K_M is 5.4 GB, Q8_0 is 8.1 GB, BF16 is 15.2 GB.

What context length does Med Qwen2 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 Med Qwen2 GGUF?

The files are on Hugging Face in the Echelon-AI/Med-Qwen2-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 Med Qwen2 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.

Similar models

Browse all →

More from Echelon-AI

All by Echelon-AI →

More Qwen models

All Qwen →

Other small models

All small models →