WI

WizardCoder Python 34B V1.0

WizardcoderGGUF by tsqnUpdated 2025-02-07
Download on Hugging Face
Parameters33.7B
Context16K
Layers48
Architecturellama
Smallest quant19.1 GB
Quick answer

WizardCoder Python 34B V1.0 needs about 21.2 GB of memory at Q4_0 (a 19.1 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 2 quants, from 19.1 GB (Q4_0) to 23.8 GB (Q5_K_M).

WizardCoder Python 34B V1.0 is a 33.7B-parameter Wizardcoder model in GGUF format, quantized by tsqn. Its trained context length is 16K tokens. The repository has 2 quant files, from 19.1 GB (Q4_0) to 23.8 GB (Q5_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_019.1 GB (4 parts) 21.2 GB
Too big Get file →
Q5_K_M23.8 GB (5 parts) 25.9 GB
Too big Get file →

What GPU do you need for WizardCoder Python 34B 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: 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: the best quant that fits is Q4_0 (19.1 GB file, about 21.2 GB in use).
  • 32 GB VRAM: the best quant that fits is Q5_K_M (23.8 GB file, about 25.9 GB in use).

Which WizardCoder Python 34B V1.0 quant should you choose?

Q4_0 (19.1 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters33.7B
Layers48
Trained context16,384 tokens
KV cache (fp16)192 KB per token

Source

Quantized bytsqn
Licensellama2
Downloads (HF)20
Last updated2025-02-07

Frequently asked questions about WizardCoder Python 34B V1.0

How much VRAM does WizardCoder Python 34B V1.0 need?

About 21.2 GB at Q4_0 with an 8K context window. That is the 19.1 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 WizardCoder Python 34B V1.0 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 21.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of WizardCoder Python 34B V1.0 GGUF?

It depends on the quant: Q4_0 is 19.1 GB, Q5_K_M is 23.8 GB.

What context length does WizardCoder Python 34B V1.0 support?

The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 1.6 GB at 8K and 3.2 GB at 16K.

Where can I download WizardCoder Python 34B V1.0 GGUF?

The files are on Hugging Face in the tsqn/WizardCoder-Python-34B-V1.0-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 WizardCoder Python 34B V1.0 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.

Other GGUFs of WizardCoder-Python-34B-V1.0

Similar models

Browse all →

More from tsqn

All by tsqn →

More Wizardcoder models

All Wizardcoder →

Other medium models

All medium models →