QW

Qwen3 Next REAP 25B A3B Thinking

QwenGGUF by lovedheartUpdated 2026-01-27
Download on Hugging Face
Parameters26.5B
Context256K
Layers48
Architectureqwen3next
Smallest quant10.5 GB
Quick answer

Qwen3 Next REAP 25B A3B Thinking needs about 18.9 GB of memory at MXFP4 (a 17.6 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 10 quants, from 10.5 GB (IQ1_S) to 53.0 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.2 GB.

Qwen3 Next REAP 25B A3B Thinking is a 26.5B-parameter Qwen model in GGUF format, quantized by lovedheart. Its trained context length is 256K tokens. The repository has 10 quant files, from 10.5 GB (IQ1_S) to 53.0 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S10.5 GB 11.8 GB
Too big Get file →
IQ1_M11.4 GB 12.7 GB
Too big Get file →
Q2_K13.6 GB 14.9 GB
Too big Get file →
Q3_K_XL16.3 GB 17.6 GB
Too big Get file →
MXFP417.6 GB 18.9 GB
Too big Get file →
Q4_K_XL19.3 GB 20.6 GB
Too big Get file →
Q5_K_XL22.0 GB 23.3 GB
Too big Get file →
Q6_K24.5 GB 25.8 GB
Too big Get file →
Q8_030.5 GB 31.8 GB
Too big Get file →
BF1653.0 GB 54.3 GB
Too big Get file →

What GPU do you need for Qwen3 Next REAP 25B 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: the best quant that fits is IQ1_S (10.5 GB file, about 11.8 GB in use).
  • 16 GB VRAM: the best quant that fits is Q2_K (13.6 GB file, about 14.9 GB in use).
  • 24 GB VRAM: the best quant that fits is Q5_K_XL (22.0 GB file, about 23.3 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (30.5 GB file, about 31.8 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (30.5 GB file, about 31.8 GB in use).

Which Qwen3 Next REAP 25B A3B Thinking quant should you choose?

MXFP4 (17.6 GB) is the middle option in this repository. Lower bit counts mean smaller files and more quality loss.

If memory is tight, the smallest file is IQ1_S at 10.5 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen3next
Parameters26.5B (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)155
Last updated2026-01-27

Frequently asked questions about Qwen3 Next REAP 25B A3B Thinking

How much VRAM does Qwen3 Next REAP 25B A3B Thinking need?

About 18.9 GB at MXFP4 with an 8K context window. That is the 17.6 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 25B A3B Thinking on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 11.8 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Qwen3 Next REAP 25B A3B Thinking GGUF?

It depends on the quant: IQ1_S is 10.5 GB, IQ1_M is 11.4 GB, Q2_K is 13.6 GB, Q3_K_XL is 16.3 GB, MXFP4 is 17.6 GB, Q4_K_XL is 19.3 GB and 4 more.

What context length does Qwen3 Next REAP 25B 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 25B A3B Thinking GGUF?

The files are on Hugging Face in the lovedheart/Qwen3-Next-REAP-25B-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 25B 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 →