QW

Qwen3 23B A3B Thinking REAP ptbr

QwenGGUF by xande-pUpdated 2026-02-07
Download on Hugging Face
Parameters23.3B
Context256K
Layers—
Architectureqwen3moe
Smallest quant13.3 GB
Quick answer

Qwen3 23B A3B Thinking REAP ptbr needs about 15.4 GB of memory at Q4_K_S (a 13.3 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 4 quants, from 13.3 GB (Q4_0) to 19.1 GB (Q6_K).

Qwen3 23B A3B Thinking REAP ptbr is a 23.3B-parameter Qwen model in GGUF format, quantized by xande-p. Its trained context length is 256K tokens. The repository has 4 quant files, from 13.3 GB (Q4_0) to 19.1 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_013.3 GB 15.4 GB
Too big Get file →
Q4_K_S13.3 GB 15.4 GB
Too big Get file →
Q4_114.7 GB 16.9 GB
Too big Get file →
Q6_K19.1 GB 21.9 GB
Too big Get file →

What GPU do you need for Qwen3 23B A3B Thinking REAP ptbr?

These figures add the file size, an fp16 KV cache at an 8K context window 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: the best quant that fits is Q4_K_S (13.3 GB file, about 15.4 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K (19.1 GB file, about 21.9 GB in use).

Which Qwen3 23B A3B Thinking REAP ptbr quant should you choose?

Q4_K_S (13.3 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

If memory is tight, the smallest file is Q4_0 at 13.3 GB, with the quality trade-offs that come with fewer bits. 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

Architectureqwen3moe
Parameters23.3B
Trained context262,144 tokens

Source

Quantized byxande-p
FamilyQwen
Downloads (HF)0
Last updated2026-02-07

Frequently asked questions about Qwen3 23B A3B Thinking REAP ptbr

How much VRAM does Qwen3 23B A3B Thinking REAP ptbr need?

About 15.4 GB at Q4_K_S with an 8K context window. That is the 13.3 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 Qwen3 23B A3B Thinking REAP ptbr on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 15.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Qwen3 23B A3B Thinking REAP ptbr GGUF?

It depends on the quant: Q4_0 is 13.3 GB, Q4_K_S is 13.3 GB, Q4_1 is 14.7 GB, Q6_K is 19.1 GB.

What context length does Qwen3 23B A3B Thinking REAP ptbr support?

The GGUF header lists a trained context length of 262,144 tokens (256K).

Where can I download Qwen3 23B A3B Thinking REAP ptbr GGUF?

The files are on Hugging Face in the xande-p/Qwen3-23B-A3B-Thinking-REAP-ptbr-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 xande-p

All by xande-p →

More Qwen models

All Qwen →

Other medium models

All medium models →