QW

Qwen3.5 24B A3B REAP 0.32

QwenGGUF by sandeshrajxUpdated 2026-03-07
Download on Hugging Face
Parameters18.5B
Context256K
Layers40
Architectureqwen35moe
Smallest quant12.1 GB
Quick answer

Qwen3.5 24B A3B REAP 0.32 needs about 16.1 GB of memory at Q4_K_M (a 15.0 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 5 quants, from 12.1 GB to 15.7 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.

Qwen3.5 24B A3B REAP 0.32 is a 18.5B-parameter Qwen model in GGUF format, quantized by sandeshrajx. Its trained context length is 256K tokens. The repository has 5 quant files, from 12.1 GB to 15.7 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—12.1 GB 13.3 GB
Too big Get file →
—14.9 GB 16.1 GB
Too big Get file →
Q4_K_M15.0 GB 16.1 GB
Too big Get file →
—15.3 GB 16.4 GB
Too big Get file →
—15.7 GB 16.9 GB
Too big Get file →

What GPU do you need for Qwen3.5 24B A3B REAP 0.32?

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: the best quant that fits is the main file (12.1 GB file, about 13.3 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (15.7 GB file, about 16.9 GB in use).

Which Qwen3.5 24B A3B REAP 0.32 quant should you choose?

Q4_K_M is the usual starting point for Qwen3.5 24B A3B REAP 0.32: it balances file size and quality well. Here it is a 15.0 GB file.

If memory is tight, the smallest file is the first one in the table at 12.1 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35moe
Parameters18.5B (approximate, mixture of experts)
Active parameters3B
Layers40
Trained context262,144 tokens
KV cache (fp16)80 KB per token

Source

Quantized bysandeshrajx
FamilyQwen
Licenseapache-2.0
Downloads (HF)160
Last updated2026-03-07

Frequently asked questions about Qwen3.5 24B A3B REAP 0.32

How much VRAM does Qwen3.5 24B A3B REAP 0.32 need?

About 16.1 GB at Q4_K_M with an 8K context window. That is the 15.0 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 Qwen3.5 24B A3B REAP 0.32 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 13.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Qwen3.5 24B A3B REAP 0.32 GGUF?

It depends on the quant: file is 12.1 GB, file is 14.9 GB, Q4_K_M is 15.0 GB, file is 15.3 GB, file is 15.7 GB.

What context length does Qwen3.5 24B A3B REAP 0.32 support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.7 GB at 8K and 2.7 GB at 32K.

Where can I download Qwen3.5 24B A3B REAP 0.32 GGUF?

The files are on Hugging Face in the sandeshrajx/Qwen3.5-24B-A3B-REAP-0.32-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 Qwen3.5 24B A3B REAP 0.32 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 Qwen3.5-35B-A3B

Similar models

Browse all →

More from sandeshrajx

All by sandeshrajx →

More Qwen models

All Qwen →

Other medium models

All medium models →