QW

Smoothie Qwen3 Next 80B A3B Instruct

QwenGGUF by mradermacherUpdated 2025-12-21
Download on Hugging Face
Parameters80B
Context256K
Layers48
Architectureqwen3next
Smallest quant0.5 GB
Quick answer

Smoothie 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 24 quants, from 0.5 GB to 65.5 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 3.2 GB.

Smoothie Qwen3 Next 80B A3B Instruct – 80B parameter LLM in GGUF format

Smoothie Qwen3 Next 80B A3B Instruct is an 80B parameter model with 3B active parameters and mixture of experts. It was trained on 262144 context tokens and is released under the Apache‑2.0 license.

Good at

  • Large context handling
  • Instruction following
  • Mixture of experts support

Limits

  • Requires high VRAM for full precision
  • No vision capabilities
  • Large model size

Best for

  • Long‑form content generation
  • Complex instruction tasks
  • Research on expert models

Who it’s for. Developers needing a large instruction‑following model with extensive context. Requires access to GGUF‑compatible inference engines such as llama.cpp.

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 →
Q4_150.0 GB 51.3 GB
Too big Get file →
Q5_K_S55.0 GB 56.3 GB
Too big Get file →
Q5_K_M56.7 GB 58.0 GB
Too big Get file →
Q6_K65.5 GB 66.8 GB
Too big Get file →

For 8 GB VRAM, the smallest usable quant is IQ1_S, which needs about 17.5 GB at 8k context. With 12 GB VRAM, IQ2_XXS (22.3 GB) is the next option. For 16 GB VRAM or more, Q2_K (30.4 GB) or higher quants can be used. Memory estimates are approximate.

What GPU do you need for Smoothie 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 Smoothie Qwen3 Next 80B A3B Instruct quant should you choose?

Q4_K_M is the usual starting point for Smoothie 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
Parameters80B (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)1,006
Last updated2025-12-21

Frequently asked questions about Smoothie Qwen3 Next 80B A3B Instruct

How much VRAM does Smoothie 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 Smoothie 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 Smoothie 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 18 more.

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

The files are on Hugging Face in the mradermacher/Smoothie-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 Smoothie 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 this model on 8 GB VRAM?

The smallest quant with reasonable memory is IQ1_S, which requires about 17.5 GB at 8k context, so 8 GB VRAM is insufficient.

Does it support vision?

No vision support is indicated.

What license applies?

Apache‑2.0 license.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Qwen models

All Qwen →

Other large models

All large models →