MA

Magicoder S CL 7B

MagicoderGGUF by eramaxUpdated 2023-12-05
Download on Hugging Face
Parameters6.74B
Context16K
Layers32
Architecturellama
Smallest quant4.8 GB
Quick answer

Magicoder S CL 7B needs about 9.6 GB of memory at Q5_K_M (a 4.8 GB file) with an 8K context window, so it fits on a 12 GB GPU.

Magicoder S CL 7B is a 6.74B-parameter Magicoder model in GGUF format, quantized by eramax. Its trained context length is 16K tokens. The repository has 1 quant file, from 4.8 GB (Q5_K_M) to 4.8 GB (Q5_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_M4.8 GB 9.6 GB
Too big Get file →

What GPU do you need for Magicoder S CL 7B?

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_M (4.8 GB file, about 9.6 GB in use).

Which Magicoder S CL 7B quant should you choose?

Q5_K_M (4.8 GB) is the middle option in this repository. 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

Architecturellama
Parameters6.74B
Layers32
Trained context16,384 tokens
KV cache (fp16)512 KB per token

Source

Quantized byeramax
FamilyMagicoder
Licensellama2
Downloads (HF)16
Last updated2023-12-05

Frequently asked questions about Magicoder S CL 7B

How much VRAM does Magicoder S CL 7B need?

About 9.6 GB at Q5_K_M 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 Magicoder S CL 7B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Magicoder S CL 7B GGUF?

It depends on the quant: Q5_K_M is 4.8 GB.

What context length does Magicoder S CL 7B support?

The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 4.3 GB at 8K and 8.6 GB at 16K.

Where can I download Magicoder S CL 7B GGUF?

The files are on Hugging Face in the eramax/Magicoder-S-CL-7B-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 Magicoder S CL 7B use?

Hugging Face lists the license as llama2. 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 eramax

All by eramax →

More Magicoder models

All Magicoder →

Other small models

All small models →