Qwen3-Coder-Next needs about 49.8 GB of memory at Q4_K_M (a 48.5 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 38 quants, from 18.9 GB (TQ1_0) to 159.5 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.2 GB.
Qwen3-Coder-Next – 80B parameter coding model with 262k context length
Qwen3-Coder-Next is an 80B parameter language model optimized for coding tasks. It uses a mixture of experts with only 3B activated parameters, providing efficient inference. The model supports a 262,144 token context and is released under Apache‑2.0.
Good at
- Long‑horizon coding reasoning
- Tool‑calling and execution recovery
- IDE integration with large context
Limits
- Requires >45 GB unified memory for 4‑bit quants
- No vision or non‑coding capabilities
- Only non‑thinking mode output
Best for
- Local coding assistants
- Complex script generation
- IDE plugin development
Who it’s for. Developers and research teams needing a local coding agent with large context. The model is suitable for environments where 80B parameters are too large but 3B active parameters suffice.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| TQ1_0 | 18.9 GB | 20.2 GB | Too big | Get file → | |
| IQ1_S | 21.5 GB | 22.8 GB | Too big | Get file → | |
| IQ1_M | 21.7 GB | 23.0 GB | Too big | Get file → | |
| IQ2_XXS | 23.3 GB | 24.6 GB | Too big | Get file → | |
| IQ2_M | 25.0 GB | 26.3 GB | Too big | Get file → | |
| Q2_K_XL | 26.8 GB | 28.1 GB | Too big | Get file → | |
| IQ3_XXS | 28.5 GB | 29.8 GB | Too big | Get file → | |
| Q2_K | 29.2 GB | 30.5 GB | Too big | Get file → | |
| Q2_K_L | 29.3 GB | 30.6 GB | Too big | Get file → | |
| IQ3_S | 29.7 GB | 31.0 GB | Too big | Get file → | |
| Q3_K_S | 33.3 GB | 34.6 GB | Too big | Get file → | |
| Q3_K_S | 34.6 GB | 35.9 GB | Too big | Get file → | |
| Q3_K_M | 35.9 GB | 37.2 GB | Too big | Get file → | |
| Q3_K_XL | 36.3 GB | 37.6 GB | Too big | Get file → | |
| Q3_K_M | 38.3 GB | 39.6 GB | Too big | Get file → | |
| IQ4_XS | 38.4 GB | 39.7 GB | Too big | Get file → | |
| IQ4_NL | 39.2 GB | 40.5 GB | Too big | Get file → | |
| IQ4_XS | 42.7 GB | 44.0 GB | Too big | Get file → | |
| IQ4_NL | 45.1 GB | 46.4 GB | Too big | Get file → | |
| Q4_0 | 45.3 GB | 46.6 GB | Too big | Get file → | |
| Q4_K_S | 45.5 GB | 46.8 GB | Too big | Get file → | |
| Q4_K_S | 46.1 GB | 47.4 GB | Too big | Get file → | |
| MXFP4_MOE | 48.0 GB | 49.3 GB | Too big | Get file → | |
| Q4_K_M | 48.5 GB | 49.8 GB | Too big | Get file → | |
| Q4_K_M | 49.3 GB | 50.6 GB | Too big | Get file → | |
| Q4_K_XL | 49.6 GB | 50.9 GB | Too big | Get file → | |
| Q4_1 | 50.1 GB (3 parts) | 51.4 GB | Too big | Get file → | |
| Q5_K_S | 55.1 GB (3 parts) | 56.4 GB | Too big | Get file → | |
| Q5_K_S | 55.8 GB (3 parts) | 57.1 GB | Too big | Get file → | |
| Q5_K_M | 56.8 GB (3 parts) | 58.2 GB | Too big | Get file → | |
| Q5_K_M | 59.2 GB (3 parts) | 60.5 GB | Too big | Get file → | |
| Q5_K_XL | 59.5 GB (3 parts) | 60.8 GB | Too big | Get file → | |
| Q6_K | 65.6 GB (3 parts) | 66.9 GB | Too big | Get file → | |
| Q6_K | 65.8 GB (3 parts) | 67.1 GB | Too big | Get file → | |
| Q6_K_XL | 73.1 GB (3 parts) | 74.4 GB | Too big | Get file → | |
| Q8_0 | 84.8 GB (3 parts) | 86.1 GB | Too big | Get file → | |
| Q8_K_XL | 86.3 GB (3 parts) | 87.7 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_S (≈46 GB unified memory). For 16 GB VRAM, Q4_K_M (≈50 GB). For 30 GB+ unified memory, Q2_K_XL (≈51 GB) or Q3_K_S (≈35 GB).
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: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: the best quant that fits is IQ1_M (21.7 GB file, about 23.0 GB in use).
- 32 GB VRAM: the best quant that fits is IQ3_S (29.7 GB file, about 31.0 GB in use).
- 48 GB VRAM: the best quant that fits is Q4_K_S (46.1 GB file, about 47.4 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 48.5 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 TQ1_0 at 18.9 GB, with the quality trade-offs that come with fewer bits. Lower bit counts mean smaller files and more quality loss.
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 49.8 GB at Q4_K_M with an 8K context window. That is the 48.5 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?
Not at an 8K context. The smallest file needs about 20.2 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Qwen3-Coder-Next GGUF?
It depends on the quant: TQ1_0 is 18.9 GB, IQ1_S is 21.5 GB, IQ1_M is 21.7 GB, IQ2_XXS is 23.3 GB, IQ2_M is 25.0 GB, Q2_K_XL is 26.8 GB and 32 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 unsloth/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?
No, the smallest 4‑bit quant requires over 45 GB unified memory. 8 GB VRAM is insufficient.
Does the model support image inputs?
No, it only handles text and coding tasks.
What license applies to this model?
Apache‑2.0, allowing free use and modification.