Qwen3-Coder-Next needs about 50.5 GB of memory at Q4_K_M (a 49.2 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 19 quants, from 0.5 GB to 159.5 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.2 GB.
Qwen3-Coder-Next – 79.7B parameter Mixture of Experts model
Qwen3-Coder-Next is a 79.7B parameter Mixture of Experts model from the Qwen family. It supports coding and tool usage abilities and was generated with llama.cpp commit `8872ad212`. The model offers a large context window of 262144 tokens.
Good at
- Large context handling
- Coding tasks
- Tool integration
Limits
- No vision support
- Requires high VRAM for full precision
- License is apache-2.0
Best for
- Complex code generation
- Long‑form documentation
- API tool usage
Who it’s for. Developers and researchers needing a large‑scale coding model with extensive context. Suitable for environments that can accommodate the memory demands of a 79.7B parameter Mixture of Experts architecture.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.5 GB | 1.8 GB | Fits | Get file → | |
| IQ2_S | 31.5 GB | 32.8 GB | Too big | Get file → | |
| IQ2_XS | 32.4 GB | 33.7 GB | Too big | Get file → | |
| IQ3_XXS | 37.6 GB | 38.9 GB | Too big | Get file → | |
| IQ3_S | 40.6 GB | 41.9 GB | Too big | Get file → | |
| IQ4_XS | 42.7 GB | 44.0 GB | Too big | Get file → | |
| Q4_0 | 45.0 GB | 46.3 GB | Too big | Get file → | |
| IQ4_NL | 45.0 GB | 46.3 GB | Too big | Get file → | |
| Q4_K_S | 47.2 GB | 48.5 GB | Too big | Get file → | |
| Q4_K_M | 49.2 GB | 50.5 GB | Too big | Get file → | |
| Q4_1 | 50.0 GB | 51.3 GB | Too big | Get file → | |
| Q5_0 | 55.0 GB (2 parts) | 56.3 GB | Too big | Get file → | |
| Q5_K_M | 58.3 GB (2 parts) | 59.6 GB | Too big | Get file → | |
| Q5_1 | 59.9 GB (2 parts) | 61.2 GB | Too big | Get file → | |
| Q6_K_M | 65.5 GB (2 parts) | 66.8 GB | Too big | Get file → | |
| Q8_0 | 84.8 GB (2 parts) | 86.1 GB | Too big | Get file → | |
| BF16 | 99.7 GB (3 parts) | 101.0 GB | Too big | Get file → | |
| F16 | 99.7 GB (3 parts) | 101.0 GB | Too big | Get file → | |
| BF16 | 159.5 GB (4 parts) | 160.8 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (49.2 GB file, ~50.5 GB memory at 8 k context). For 16 GB VRAM, Q5_K_M (58.26 GB file, ~59.6 GB memory) is a good balance. For 32 GB VRAM, Q8_0 (84.81 GB file, ~86.1 GB memory) provides higher precision.
What GPU do you need for Qwen3-Coder-Next?
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 the main file (0.5 GB file, about 1.8 GB in use).
- 32 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 1.8 GB in use).
- 48 GB VRAM: the best quant that fits is IQ4_NL (45.0 GB file, about 46.3 GB in use).
Which Qwen3-Coder-Next quant should you choose?
Q4_K_M is the usual starting point for Qwen3-Coder-Next: it balances file size and quality well. Here it is a 49.2 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-Coder-Next
How much VRAM does Qwen3-Coder-Next need?
About 50.5 GB at Q4_K_M with an 8K context window. That is the 49.2 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-Coder-Next 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-Coder-Next GGUF?
It depends on the quant: file is 0.5 GB, IQ2_S is 31.5 GB, IQ2_XS is 32.4 GB, IQ3_XXS is 37.6 GB, IQ3_S is 40.6 GB, IQ4_XS is 42.7 GB and 13 more.
What context length does Qwen3-Coder-Next 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-Coder-Next GGUF?
The files are on Hugging Face in the Mungert/Qwen3-Coder-Next-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-Coder-Next 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-Coder-Next on 8 GB VRAM?
Only the Q4_K_M quantization can fit within 8 GB VRAM, but it requires ~50.5 GB of memory at 8 k context, so it is not feasible on 8 GB VRAM.
Does the model support vision tasks?
No, the model does not have vision capabilities.
What license applies to this model?
The model is released under the apache-2.0 license.