QW

Qwen3 Next 80B A3B Instruct

QwenGGUF by mradermacherUpdated 2025-12-04
Download on Hugging Face
Parameters79.7B
Context256K
Layers48
Architectureqwen3next
Smallest quant0.5 GB
Quick answer

Qwen3 Next 80B A3B Instruct needs about 49.7 GB of memory at Q4_K_M (a 48.4 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 20 quants, from 0.5 GB to 48.4 GB (Q4_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 3.2 GB.

Qwen3 Next 80B A3B Instruct – 80B parameter LLM with ultra‑long context

Qwen3 Next 80B A3B Instruct is a 79.7B parameter causal language model with a 262144 token context window. It is a mixture‑of‑experts model with only 3B active parameters. The model supports instruct mode and tool usage.

Good at

  • Ultra‑long context reasoning
  • Tool‑enabled instruction following
  • Large‑scale inference with low activation ratio

Limits

  • No vision support
  • Requires high VRAM for large quants
  • Licensed under apache‑2.0

Best for

  • Chatbots needing 256K token context
  • Long‑form content generation
  • Agentic task planning

Who it’s for. Developers building AI agents that need to process very long documents or conversations. Researchers testing MoE efficiency in large models.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.5 GB 1.8 GB
Fits Get file →
IQ1_S16.2 GB 17.5 GB
Too big Get file →
IQ1_M18.0 GB 19.3 GB
Too big Get file →
IQ2_XXS21.0 GB 22.3 GB
Too big Get file →
IQ2_XS23.4 GB 24.7 GB
Too big Get file →
IQ2_S23.6 GB 24.9 GB
Too big Get file →
IQ2_M26.1 GB 27.4 GB
Too big Get file →
Q2_K_S27.3 GB 28.6 GB
Too big Get file →
Q2_K29.1 GB 30.4 GB
Too big Get file →
IQ3_XXS30.8 GB 32.1 GB
Too big Get file →
IQ3_XS32.7 GB 34.0 GB
Too big Get file →
Q3_K_S34.5 GB 35.9 GB
Too big Get file →
IQ3_S34.5 GB 35.9 GB
Too big Get file →
IQ3_M35.0 GB 36.3 GB
Too big Get file →
Q3_K_M38.2 GB 39.5 GB
Too big Get file →
Q3_K_L41.2 GB 42.5 GB
Too big Get file →
IQ4_XS42.6 GB 43.9 GB
Too big Get file →
Q4_045.3 GB 46.6 GB
Too big Get file →
Q4_K_S45.5 GB 46.8 GB
Too big Get file →
Q4_K_M48.4 GB 49.7 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (16.18 GB file, 17.5 GB memory at 8K context). For 16 GB VRAM, IQ2_XXS (21.01 GB file, 22.3 GB memory) or IQ2_XS (23.43 GB file, 24.7 GB memory). Larger VRAM allows higher‑quality quants such as Q3_K_M (38.19 GB file, 39.5 GB memory).

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

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 (0.5 GB file, about 1.8 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 1.8 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 1.8 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 1.8 GB in use).
  • 16 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 1.8 GB in use).
  • 24 GB VRAM: the best quant that fits is IQ2_XXS (21.0 GB file, about 22.3 GB in use).
  • 32 GB VRAM: the best quant that fits is Q2_K (29.1 GB file, about 30.4 GB in use).
  • 48 GB VRAM: the best quant that fits is Q4_K_S (45.5 GB file, about 46.8 GB in use).

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

Q4_K_M is the usual starting point for Qwen3 Next 80B A3B Instruct: it balances file size and quality well. Here it is a 48.4 GB file.

If memory is tight, the smallest file is the first one in the table at 0.5 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
Parameters79.7B (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)1,547
Last updated2025-12-04

Frequently asked questions about Qwen3 Next 80B A3B Instruct

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

About 49.7 GB at Q4_K_M with an 8K context window. That is the 48.4 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 on an 8 GB GPU?

Yes, with the smaller files: the 0.5 GB file needs about 1.8 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 GGUF?

It depends on the quant: file is 0.5 GB, IQ1_S is 16.2 GB, IQ1_M is 18.0 GB, IQ2_XXS is 21.0 GB, IQ2_XS is 23.4 GB, IQ2_S is 23.6 GB and 14 more.

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

The files are on Hugging Face in the mradermacher/Qwen3-Next-80B-A3B-Instruct-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 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 Qwen3 Next 80B A3B Instruct on 8 GB VRAM?

Use the IQ1_S quant; it requires about 17.5 GB memory at 8K context, which is close to 8 GB VRAM but may need CPU fallback.

Does this model support vision tasks?

No, the model only supports text and tool usage; it does not generate image tokens.

What license applies to this model?

The model is released under the apache‑2.0 license.

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

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Qwen models

All Qwen →

Other large models

All large models →