QW

Qwen3 Next REAP 15B A3B Thinking

QwenGGUF by lovedheartUpdated 2026-01-25
Download on Hugging Face
Parameters16.8B
Context256K
Layers48
Architectureqwen3next
Smallest quant11.7 GB
Quick answer

Qwen3 Next REAP 15B A3B Thinking needs about 14.9 GB of memory at Q4_K_XL (a 13.6 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 6 quants, from 11.7 GB (Q3_K_XL) to 33.7 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.2 GB.

Qwen3 Next REAP 15B A3B Thinking is a 16.8B-parameter Qwen model in GGUF format, quantized by lovedheart. Its trained context length is 256K tokens. The repository has 6 quant files, from 11.7 GB (Q3_K_XL) to 33.7 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_XL11.7 GB 13.0 GB
Too big Get file →
MXFP4_MOE12.5 GB 13.8 GB
Too big Get file →
Q4_K_XL13.6 GB 14.9 GB
Too big Get file →
Q6_K16.7 GB 18.0 GB
Too big Get file →
Q8_020.2 GB 21.5 GB
Too big Get file →
BF1633.7 GB 35.0 GB
Too big Get file →

What GPU do you need for Qwen3 Next REAP 15B A3B Thinking?

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 Q4_K_XL (13.6 GB file, about 14.9 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (20.2 GB file, about 21.5 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (20.2 GB file, about 21.5 GB in use).
  • 48 GB VRAM: the best quant that fits is BF16 (33.7 GB file, about 35.0 GB in use).

Which Qwen3 Next REAP 15B A3B Thinking quant should you choose?

Q4_K_XL (13.6 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 Q3_K_XL at 11.7 GB, with the quality trade-offs that come with fewer bits. 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

Architectureqwen3next
Parameters16.8B (approximate, mixture of experts)
Active parameters3B
Layers48
Trained context262,144 tokens
KV cache (fp16)96 KB per token

Source

Quantized bylovedheart
FamilyQwen
Licenseapache-2.0
Downloads (HF)116
Last updated2026-01-25

Frequently asked questions about Qwen3 Next REAP 15B A3B Thinking

How much VRAM does Qwen3 Next REAP 15B A3B Thinking need?

About 14.9 GB at Q4_K_XL with an 8K context window. That is the 13.6 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 Next REAP 15B A3B Thinking on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 13.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Qwen3 Next REAP 15B A3B Thinking GGUF?

It depends on the quant: Q3_K_XL is 11.7 GB, MXFP4_MOE is 12.5 GB, Q4_K_XL is 13.6 GB, Q6_K is 16.7 GB, Q8_0 is 20.2 GB, BF16 is 33.7 GB.

What context length does Qwen3 Next REAP 15B A3B Thinking support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.8 GB at 8K and 3.2 GB at 32K.

Where can I download Qwen3 Next REAP 15B A3B Thinking GGUF?

The files are on Hugging Face in the lovedheart/Qwen3-Next-REAP-15B-A3B-Thinking-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 Next REAP 15B A3B Thinking 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-Next-80B-A3B-Thinking

Similar models

Browse all →

More from lovedheart

All by lovedheart →

More Qwen models

All Qwen →

Other medium models

All medium models →