QW

Qwen3 Next 80B A3B Instruct REAP

QwenGGUF by mradermacherUpdated 2026-02-02
Download on Hugging Face
Parameters60.3B
Context256K
Layers48
Architectureqwen3next
Smallest quant0.3 GB
Quick answer

Qwen3 Next 80B A3B Instruct REAP needs about 38.0 GB of memory at Q4_K_M (a 36.7 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 24 quants, from 0.3 GB to 49.6 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 3.2 GB.

Qwen3 Next 80B A3B Instruct REAP – a compressed 60B‑parameter MoE model

Qwen3 Next 80B A3B Instruct REAP is a compressed version of Qwen/Qwen3-Next-80B-A3B-Instruct. It reduces experts from 512 to 384, lowering storage to 60B params (120GB) and GPU memory by roughly 25%. The model retains >=94% of the original performance.

Good at

  • Tool usage
  • Large context handling
  • Efficient inference with quantization

Limits

  • Requires 262144 token context
  • No vision support
  • Apache‑2.0 license

Best for

  • Chatbot assistants
  • Code generation with tool calls
  • Long‑form content creation

Who it’s for. Developers and researchers needing a large‑scale instruction‑tuned model with reduced memory footprint. Suitable for local deployment using llama.cpp with available GGUF quantizations.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.3 GB 1.6 GB
Fits Get file →
IQ1_S12.3 GB 13.6 GB
Too big Get file →
IQ1_M13.7 GB 15.0 GB
Too big Get file →
IQ2_XXS16.0 GB 17.3 GB
Too big Get file →
IQ2_XS17.8 GB 19.1 GB
Too big Get file →
IQ2_S17.9 GB 19.3 GB
Too big Get file →
IQ2_M19.8 GB 21.1 GB
Too big Get file →
Q2_K_S20.7 GB 22.0 GB
Too big Get file →
Q2_K22.1 GB 23.4 GB
Too big Get file →
IQ3_XXS23.3 GB 24.7 GB
Too big Get file →
IQ3_XS24.8 GB 26.1 GB
Too big Get file →
Q3_K_S26.2 GB 27.5 GB
Too big Get file →
IQ3_S26.2 GB 27.5 GB
Too big Get file →
IQ3_M26.6 GB 27.9 GB
Too big Get file →
Q3_K_M29.0 GB 30.3 GB
Too big Get file →
Q3_K_L31.3 GB 32.6 GB
Too big Get file →
IQ4_XS32.3 GB 33.6 GB
Too big Get file →
Q4_034.3 GB 35.6 GB
Too big Get file →
Q4_K_S34.5 GB 35.8 GB
Too big Get file →
Q4_K_M36.7 GB 38.0 GB
Too big Get file →
Q4_137.9 GB 39.2 GB
Too big Get file →
Q5_K_S41.7 GB 43.0 GB
Too big Get file →
Q5_K_M43.0 GB 44.3 GB
Too big Get file →
Q6_K49.6 GB 50.9 GB
Too big Get file →

For 8‑GB VRAM, use IQ1_S (12.31 GB file, 13.6 GB memory at 8k context). For 16‑GB VRAM, IQ2_S (17.95 GB file, 19.3 GB memory) or Q2_K_S (20.67 GB file, 22 GB memory). For 24‑GB VRAM, Q3_K_M (29.01 GB file, 30.3 GB memory) or Q4_K_M (36.73 GB file, 38 GB memory). Estimates are approximate.

What GPU do you need for Qwen3 Next 80B A3B Instruct REAP?

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: the best quant that fits is the main file (0.3 GB file, about 1.6 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.3 GB file, about 1.6 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.3 GB file, about 1.6 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (0.3 GB file, about 1.6 GB in use).
  • 16 GB VRAM: the best quant that fits is IQ1_M (13.7 GB file, about 15.0 GB in use).
  • 24 GB VRAM: the best quant that fits is Q2_K (22.1 GB file, about 23.4 GB in use).
  • 32 GB VRAM: the best quant that fits is Q3_K_M (29.0 GB file, about 30.3 GB in use).
  • 48 GB VRAM: the best quant that fits is Q5_K_M (43.0 GB file, about 44.3 GB in use).

Which Qwen3 Next 80B A3B Instruct REAP quant should you choose?

Q4_K_M is the usual starting point for Qwen3 Next 80B A3B Instruct REAP: it balances file size and quality well. Here it is a 36.7 GB file.

If memory is tight, the smallest file is the first one in the table at 0.3 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

Architectureqwen3next
Parameters60.3B (approximate, mixture of experts)
Active parameters3B
Layers48
Trained context262,144 tokens
KV cache (fp16)96 KB per token

Source

Quantized bymradermacher
FamilyQwen
Licenseapache-2.0
Downloads (HF)862
Last updated2026-02-02

Frequently asked questions about Qwen3 Next 80B A3B Instruct REAP

How much VRAM does Qwen3 Next 80B A3B Instruct REAP need?

About 38.0 GB at Q4_K_M with an 8K context window. That is the 36.7 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 80B A3B Instruct REAP on an 8 GB GPU?

Yes, with the smaller files: the 0.3 GB file needs about 1.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Qwen3 Next 80B A3B Instruct REAP GGUF?

It depends on the quant: file is 0.3 GB, IQ1_S is 12.3 GB, IQ1_M is 13.7 GB, IQ2_XXS is 16.0 GB, IQ2_XS is 17.8 GB, IQ2_S is 17.9 GB and 18 more.

What context length does Qwen3 Next 80B A3B Instruct REAP 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 80B A3B Instruct REAP GGUF?

The files are on Hugging Face in the mradermacher/Qwen3-Next-80B-A3B-Instruct-REAP-i1-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 80B A3B Instruct REAP 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.

Can I run this model on 8 GB VRAM?

Use the IQ1_S quant, which requires about 13.6 GB of VRAM at 8k context.

Does this model support vision tasks?

No, the model only supports text and tool usage.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of Qwen3-Next-80B-A3B-Instruct-REAP

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Qwen models

All Qwen →

Other large models

All large models →