WI

WizardCoder 15B V1.0

WizardcoderGGUF by imi1Updated 2023-09-29
Download on Hugging Face
Parameters15.8B
Context8K
Layers40
Architecturestarcoder
Smallest quant6.7 GB
Quick answer

WizardCoder 15B V1.0 needs about 10.6 GB of memory at Q4_K_M (a 10.0 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 4 quants, from 6.7 GB (Q2_K) to 10.0 GB (Q4_K_M).

WizardCoder 15B V1.0 is a 15.8B-parameter Wizardcoder model in GGUF format, quantized by imi1. Its trained context length is 8K tokens. The repository has 4 quant files, from 6.7 GB (Q2_K) to 10.0 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K6.7 GB 7.4 GB
Tight Get file →
Q3_K_M8.2 GB 8.8 GB
Too big Get file →
Q4_110.0 GB 10.6 GB
Too big Get file →
Q4_K_M10.0 GB 10.6 GB
Too big Get file →

What GPU do you need for WizardCoder 15B V1.0?

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 Q2_K (6.7 GB file, about 7.4 GB in use).
  • 12 GB VRAM: the best quant that fits is Q4_K_M (10.0 GB file, about 10.6 GB in use).

Which WizardCoder 15B V1.0 quant should you choose?

Q4_K_M is the usual starting point for WizardCoder 15B V1.0: it balances file size and quality well. Here it is a 10.0 GB file.

If memory is tight, the smallest file is Q2_K at 6.7 GB, with the quality trade-offs that come with fewer bits. 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

Architecturestarcoder
Parameters15.8B
Layers40
Trained context8,192 tokens
KV cache (fp16)20 KB per token

Source

Quantized byimi1
Downloads (HF)125
Last updated2023-09-29

Frequently asked questions about WizardCoder 15B V1.0

How much VRAM does WizardCoder 15B V1.0 need?

About 10.6 GB at Q4_K_M with an 8K context window. That is the 10.0 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 WizardCoder 15B V1.0 on an 8 GB GPU?

Yes, with Q2_K: the 6.7 GB file needs about 7.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of WizardCoder 15B V1.0 GGUF?

It depends on the quant: Q2_K is 6.7 GB, Q3_K_M is 8.2 GB, Q4_1 is 10.0 GB, Q4_K_M is 10.0 GB.

What context length does WizardCoder 15B V1.0 support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.2 GB at 8K.

Where can I download WizardCoder 15B V1.0 GGUF?

The files are on Hugging Face in the imi1/WizardCoder-15B-V1.0-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 imi1

All by imi1 →

More Wizardcoder models

All Wizardcoder →

Other medium models

All medium models →