Qwen3 Next 80B A3B Thinking needs about 50.0 GB of memory at Q4_K_M (a 48.7 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 29 quants, from 0.5 GB to 84.8 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 3.2 GB.
Qwen3-Next-80B-A3B Thinking – a large reasoning‑focused model
Qwen3-Next-80B-A3B Thinking is a 80 billion‑parameter model with a 262,144‑token context window. It is a high‑sparsity mixture‑of‑experts model that excels at complex reasoning tasks. The model is released under Apache‑2.0 and is available in multiple GGUF quantizations.
Good at
- Complex reasoning
- Long‑context understanding
- High‑sparsity MoE efficiency
Limits
- Requires large VRAM for full precision
- No vision support
- Only thinking mode
Best for
- Research on reasoning benchmarks
- Developing reasoning agents
- Testing long‑context performance
Who it’s for. Researchers and developers needing a large, reasoning‑oriented foundation model. The model is suitable for applications that require deep logical inference and extended context handling.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.5 GB | 1.8 GB | Fits | Get file → | |
| IQ1_S | 16.6 GB | 17.9 GB | Too big | Get file → | |
| IQ1_M | 17.3 GB | 18.6 GB | Too big | Get file → | |
| IQ2_XXS | 19.3 GB | 20.6 GB | Too big | Get file → | |
| IQ2_XS | 22.2 GB | 23.5 GB | Too big | Get file → | |
| IQ2_S | 23.4 GB | 24.7 GB | Too big | Get file → | |
| IQ2_M | 26.1 GB | 27.4 GB | Too big | Get file → | |
| Q2_K | 28.2 GB | 29.5 GB | Too big | Get file → | |
| Q2_K_L | 28.5 GB | 29.8 GB | Too big | Get file → | |
| IQ3_XXS | 31.7 GB | 33.0 GB | Too big | Get file → | |
| IQ3_XS | 33.0 GB | 34.3 GB | Too big | Get file → | |
| Q3_K_S | 34.9 GB | 36.2 GB | Too big | Get file → | |
| IQ3_M | 36.6 GB | 37.9 GB | Too big | Get file → | |
| Q3_K_M | 36.7 GB | 38.0 GB | Too big | Get file → | |
| Q3_K_L | 38.2 GB | 39.5 GB | Too big | Get file → | |
| Q3_K_XL | 38.5 GB | 39.8 GB | Too big | Get file → | |
| IQ4_XS | 42.8 GB | 44.2 GB | Too big | Get file → | |
| IQ4_NL | 45.3 GB | 46.6 GB | Too big | Get file → | |
| Q4_0 | 46.1 GB | 47.4 GB | Too big | Get file → | |
| Q4_K_S | 46.9 GB | 48.2 GB | Too big | Get file → | |
| Q4_K_M | 48.7 GB | 50.0 GB | Too big | Get file → | |
| Q4_K_L | 49.0 GB | 50.3 GB | Too big | Get file → | |
| Q4_1 | 50.2 GB (2 parts) | 51.5 GB | Too big | Get file → | |
| Q5_K_S | 55.2 GB (2 parts) | 56.5 GB | Too big | Get file → | |
| Q5_K_M | 57.0 GB (2 parts) | 58.3 GB | Too big | Get file → | |
| Q5_K_L | 57.2 GB (2 parts) | 58.5 GB | Too big | Get file → | |
| Q6_K | 65.8 GB (2 parts) | 67.1 GB | Too big | Get file → | |
| Q6_K_L | 65.9 GB (2 parts) | 67.2 GB | Too big | Get file → | |
| Q8_0 | 84.8 GB (3 parts) | 86.1 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (17.9 GB memory at 8 k context). For 16 GB VRAM, IQ2_XS (23.5 GB) or Q2_K (29.5 GB) are suitable. For 32 GB VRAM, Q3_K_M (38 GB) or Q4_K_L (50.3 GB) provide higher quality. Estimates are approximate.
What GPU do you need for Qwen3 Next 80B 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: 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_XS (22.2 GB file, about 23.5 GB in use).
- 32 GB VRAM: the best quant that fits is Q2_K_L (28.5 GB file, about 29.8 GB in use).
- 48 GB VRAM: the best quant that fits is Q4_0 (46.1 GB file, about 47.4 GB in use).
Which Qwen3 Next 80B A3B Thinking quant should you choose?
Q4_K_M is the usual starting point for Qwen3 Next 80B A3B Thinking: it balances file size and quality well. Here it is a 48.7 GB file.
The Q8_0 file is 84.8 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
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
Source
Frequently asked questions about Qwen3 Next 80B A3B Thinking
How much VRAM does Qwen3 Next 80B A3B Thinking need?
About 50.0 GB at Q4_K_M with an 8K context window. That is the 48.7 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 Thinking 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 Thinking GGUF?
It depends on the quant: file is 0.5 GB, IQ1_S is 16.6 GB, IQ1_M is 17.3 GB, IQ2_XXS is 19.3 GB, IQ2_XS is 22.2 GB, IQ2_S is 23.4 GB and 23 more.
What context length does Qwen3 Next 80B 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 80B A3B Thinking GGUF?
The files are on Hugging Face in the bartowski/Qwen_Qwen3-Next-80B-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 80B 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.
Can I run Qwen3-Next-80B-A3B Thinking on 8 GB VRAM?
Only the IQ1_S quantization can be run on 8 GB VRAM, as it requires about 17.9 GB of memory at 8 k context.
Does the model support vision inputs?
No, the model only supports text and is in thinking mode.
What license applies to this model?
The model is released under the Apache‑2.0 license.