QW

Openbuddy Qwen2.5Coder 32b V24.1Q

QwenGGUF by OpenBuddyUpdated 2024-12-05
Download on Hugging Face
Parameters32.8B
Context195K
Layers64
Architectureqwen2
Smallest quant15.9 GB
Quick answer

Openbuddy Qwen2.5Coder 32b V24.1Q needs about 18.6 GB of memory at Q3_K (a 15.9 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 2 quants, from 15.9 GB (Q3_K) to 34.8 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.

Openbuddy Qwen2.5Coder 32b V24.1Q is a 32.8B-parameter Qwen model in GGUF format, quantized by OpenBuddy. Its trained context length is 195K tokens. The repository has 2 quant files, from 15.9 GB (Q3_K) to 34.8 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K15.9 GB 18.6 GB
Too big Get file →
Q8_034.8 GB 37.5 GB
Too big Get file →

What GPU do you need for Openbuddy Qwen2.5Coder 32b V24.1Q?

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 Q3_K (15.9 GB file, about 18.6 GB in use).
  • 32 GB VRAM: the best quant that fits is Q3_K (15.9 GB file, about 18.6 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (34.8 GB file, about 37.5 GB in use).

Which Openbuddy Qwen2.5Coder 32b V24.1Q quant should you choose?

Q3_K (15.9 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen2
Parameters32.8B
Layers64
Trained context200,000 tokens
KV cache (fp16)256 KB per token

Source

Quantized byOpenBuddy
FamilyQwen
Licenseapache-2.0
Downloads (HF)31
Last updated2024-12-05

Frequently asked questions about Openbuddy Qwen2.5Coder 32b V24.1Q

How much VRAM does Openbuddy Qwen2.5Coder 32b V24.1Q need?

About 18.6 GB at Q3_K with an 8K context window. That is the 15.9 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 Openbuddy Qwen2.5Coder 32b V24.1Q on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 18.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Openbuddy Qwen2.5Coder 32b V24.1Q GGUF?

It depends on the quant: Q3_K is 15.9 GB, Q8_0 is 34.8 GB.

What context length does Openbuddy Qwen2.5Coder 32b V24.1Q support?

The GGUF header lists a trained context length of 200,000 tokens (195K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.6 GB at 32K.

Where can I download Openbuddy Qwen2.5Coder 32b V24.1Q GGUF?

The files are on Hugging Face in the OpenBuddy/openbuddy-qwen2.5coder-32b-v24.1q-200k-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 Openbuddy Qwen2.5Coder 32b V24.1Q 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.

Other GGUFs of openbuddy-qwen2.5coder-32b-v24.1q-200k

Similar models

Browse all →

More from OpenBuddy

All by OpenBuddy →

More Qwen models

All Qwen →

Other medium models

All medium models →