ME

MegaQwen 120B

MegaqwenGGUF by mradermacherUpdated 2024-05-06
Download on Hugging Face
Parameters125B
Context32K
Layers140
Architecturellama
Smallest quant47.8 GB
Quick answer

MegaQwen 120B needs about 85.9 GB of memory at Q2_K (a 47.8 GB file) with an 8K context window, which is more than a 48 GB GPU holds. Longer context needs more: at 32K tokens the KV cache alone adds about 150.3 GB.

MegaQwen 120B is a 125B-parameter Megaqwen model in GGUF format, quantized by mradermacher. Its trained context length is 32K tokens. The repository has 1 quant file, from 47.8 GB (Q2_K) to 47.8 GB (Q2_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K47.8 GB 85.9 GB
Too big Get file →

What GPU do you need for MegaQwen 120B?

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: no quant fits at an 8K context.
  • 48 GB VRAM: no quant fits at an 8K context.

Which MegaQwen 120B quant should you choose?

Q2_K (47.8 GB) is the middle option in this repository. 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
Parameters125B
Layers140
Trained context32,768 tokens
KV cache (fp16)4480 KB per token

Source

Quantized bymradermacher
FamilyMegaqwen
Licenseapache-2.0
Downloads (HF)130
Last updated2024-05-06

Frequently asked questions about MegaQwen 120B

How much VRAM does MegaQwen 120B need?

About 85.9 GB at Q2_K with an 8K context window. That is the 47.8 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 MegaQwen 120B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 85.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of MegaQwen 120B GGUF?

It depends on the quant: Q2_K is 47.8 GB.

What context length does MegaQwen 120B support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 37.6 GB at 8K and 150.3 GB at 32K.

Where can I download MegaQwen 120B GGUF?

The files are on Hugging Face in the mradermacher/MegaQwen-120B-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 MegaQwen 120B 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 mradermacher

All by mradermacher →

Other large models

All large models →