Qwopus3.6 27B Coder imatrix MTP needs about 13.1 GB of memory at IQ2_M (a 10.5 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 4 quants, from 9.5 GB (IQ2_XS) to 15.5 GB (IQ4_XS). Longer context needs more: at 32K tokens the KV cache alone adds about 8.7 GB.
Qwopus3.6 27B Coder imatrix MTP is a 27.3B-parameter Qwopus model in GGUF format, quantized by pearsonkyle. Its trained context length is 256K tokens. The repository has 4 quant files, from 9.5 GB (IQ2_XS) to 15.5 GB (IQ4_XS).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_XS | 9.5 GB | 12.2 GB | Too big | Get file → | |
| IQ2_M | 10.5 GB | 13.1 GB | Too big | Get file → | |
| IQ3_M | 13.0 GB | 15.7 GB | Too big | Get file → | |
| IQ4_XS | 15.5 GB | 18.2 GB | Too big | Get file → |
What GPU do you need for Qwopus3.6 27B Coder imatrix MTP?
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: the best quant that fits is IQ3_M (13.0 GB file, about 15.7 GB in use).
- 24 GB VRAM: the best quant that fits is IQ4_XS (15.5 GB file, about 18.2 GB in use).
Which Qwopus3.6 27B Coder imatrix MTP quant should you choose?
IQ2_M (10.5 GB) is the middle option in this repository. 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.
If memory is tight, the smallest file is IQ2_XS at 9.5 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 Qwopus3.6 27B Coder imatrix MTP
How much VRAM does Qwopus3.6 27B Coder imatrix MTP need?
About 13.1 GB at IQ2_M with an 8K context window. That is the 10.5 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 Qwopus3.6 27B Coder imatrix MTP on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 12.2 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Qwopus3.6 27B Coder imatrix MTP GGUF?
It depends on the quant: IQ2_XS is 9.5 GB, IQ2_M is 10.5 GB, IQ3_M is 13.0 GB, IQ4_XS is 15.5 GB.
What context length does Qwopus3.6 27B Coder imatrix MTP support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 2.2 GB at 8K and 8.7 GB at 32K.
Where can I download Qwopus3.6 27B Coder imatrix MTP GGUF?
The files are on Hugging Face in the pearsonkyle/Qwopus3.6-27B-Coder-imatrix-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 Qwopus3.6 27B Coder imatrix MTP 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.