Qwen3.6 27B A3B CoderX needs about 17.2 GB of memory at Q4_K_M (a 16.1 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 20 quants, from 8.2 GB (IQ2_XS) to 52.5 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.8 GB.
Qwen3.6 27B A3B CoderX – a long‑horizon code‑focused MoE model
Qwen3.6 27B A3B CoderX is a 27 billion‑parameter model with 184 experts per layer. It is a text‑only checkpoint derived from Qwen3.6‑35B‑A3B, retaining the same active‑parameter budget but with a different expert selection. The model is optimized for coding tasks and includes MTP for speculative decoding.
Good at
- Long‑horizon code generation
- Multi‑step competitive programming
- Large context handling
Limits
- No vision support
- Requires top‑8 routing
- Large VRAM needed for full precision
Best for
- Complex coding interviews
- Competitive programming contests
- Large‑scale code analysis
Who it’s for. Developers and researchers needing a high‑capacity code model with a long context window. The model is suitable for environments that can accommodate its VRAM requirements and support top‑8 routing.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_XS | 8.2 GB | 9.4 GB | Too big | Get file → | |
| IQ2_M | 9.1 GB | 10.2 GB | Too big | Get file → | |
| Q2_K_L | 10.4 GB | 11.5 GB | Too big | Get file → | |
| Q3_K_S | 11.5 GB | 12.7 GB | Too big | Get file → | |
| IQ3_M | 11.7 GB | 12.9 GB | Too big | Get file → | |
| Q3_K_M | 12.7 GB | 13.9 GB | Too big | Get file → | |
| Q3_K_XL | 13.2 GB | 14.4 GB | Too big | Get file → | |
| Q3_K_L | 13.7 GB | 14.9 GB | Too big | Get file → | |
| IQ4_XS | 14.2 GB | 15.4 GB | Too big | Get file → | |
| IQ4_NL | 15.0 GB | 16.2 GB | Too big | Get file → | |
| Q4_K_S | 15.1 GB | 16.3 GB | Too big | Get file → | |
| Q4_K_M | 16.1 GB | 17.2 GB | Too big | Get file → | |
| Q4_K_L | 16.4 GB | 17.6 GB | Too big | Get file → | |
| Q5_K_S | 18.2 GB | 19.3 GB | Too big | Get file → | |
| Q5_K_M | 18.7 GB | 19.9 GB | Too big | Get file → | |
| Q5_K_L | 19.0 GB | 20.2 GB | Too big | Get file → | |
| Q6_K | 21.6 GB | 22.8 GB | Too big | Get file → | |
| Q6_K_L | 21.8 GB | 23.0 GB | Too big | Get file → | |
| Q8_0 | 27.9 GB | 29.1 GB | Too big | Get file → | |
| F16 | 52.5 GB | 53.7 GB | Too big | Get file → |
For 8 GB VRAM, use IQ2_XS (8.2 GB) or IQ2_M (9.06 GB). For 12 GB VRAM, Q2_K_L (10.36 GB) or Q3_K_S (11.53 GB) are suitable. For 16 GB VRAM, Q4_K_M (16.06 GB) or Q5_K_S (18.16 GB) provide a balance of quality and memory usage. Estimates are approximate.
What GPU do you need for Qwen3.6 27B A3B CoderX?
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: the best quant that fits is Q2_K_L (10.4 GB file, about 11.5 GB in use).
- 16 GB VRAM: the best quant that fits is IQ4_XS (14.2 GB file, about 15.4 GB in use).
- 24 GB VRAM: the best quant that fits is Q6_K_L (21.8 GB file, about 23.0 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (27.9 GB file, about 29.1 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (27.9 GB file, about 29.1 GB in use).
Which Qwen3.6 27B A3B CoderX quant should you choose?
Q4_K_M is the usual starting point for Qwen3.6 27B A3B CoderX: it balances file size and quality well. Here it is a 16.1 GB file.
The Q8_0 file is 27.9 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 IQ2_XS at 8.2 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Qwen3.6 27B A3B CoderX
How much VRAM does Qwen3.6 27B A3B CoderX need?
About 17.2 GB at Q4_K_M with an 8K context window. That is the 16.1 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 Qwen3.6 27B A3B CoderX on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 9.4 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Qwen3.6 27B A3B CoderX GGUF?
It depends on the quant: IQ2_XS is 8.2 GB, IQ2_M is 9.1 GB, Q2_K_L is 10.4 GB, Q3_K_S is 11.5 GB, IQ3_M is 11.7 GB, Q3_K_M is 12.7 GB and 14 more.
What context length does Qwen3.6 27B A3B CoderX support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.7 GB at 8K and 2.8 GB at 32K.
Where can I download Qwen3.6 27B A3B CoderX GGUF?
The files are on Hugging Face in the ManniX-ITA/Qwen3.6-27B-A3B-CoderX-MTP-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 Qwen3.6 27B A3B CoderX 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 Qwen3.6 27B A3B CoderX on 8 GB VRAM?
Use the IQ2_XS or IQ2_M quantizations; they fit within 8 GB VRAM with approximate 9–10 GB memory usage at 8k context.
Does this model support vision tasks?
No, the checkpoint is text‑only; the vision tower is not included.
What routing does the model use?
The model uses top‑8 routing by default, as specified in the parent model card.