Qwopus3.6 35B A3B Coder APEX MTP needs about 24.7 GB of memory at its main file (a 23.5 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 7 quants, from 14.3 GB to 26.1 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 2.8 GB.
Qwopus3.6 35B A3B Coder APEX MTP – a coding‑agent model with built‑in MTP head
Qwopus3.6 35B A3B Coder APEX MTP is a 35B‑parameter MoE model fine‑tuned for agentic coding workflows. It includes a bundled MTP head for self‑speculative decoding and a built‑in vision encoder. The model is released under Apache‑2.0 and is intended for research and local coding‑agent evaluation.
Good at
- Token‑efficient coding workflows
- Tool‑calling and patching
- Self‑speculative decoding with MTP
Limits
- No long‑thinking mode support
- Requires recent llama.cpp for MTP
- Large VRAM needed for full MoE
Best for
- Local coding‑agent evaluation
- Tool‑calling demos
- Vision‑enabled coding tasks
Who it’s for. Researchers and developers building local coding agents who need a MoE model with efficient execution and built‑in MTP support. The model is experimental and not fully safety‑evaluated.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 14.3 GB | 15.5 GB | Too big | Get file → | |
| — | 17.3 GB | 18.5 GB | Too big | Get file → | |
| — | 17.3 GB | 18.5 GB | Too big | Get file → | |
| — | 23.5 GB | 24.7 GB | Too big | Get file → | |
| — | 23.5 GB | 24.7 GB | Too big | Get file → | |
| — | 26.1 GB | 27.2 GB | Too big | Get file → | |
| — | 26.1 GB | 27.2 GB | Too big | Get file → |
The GGUF files range from 14.27 GB to 26.06 GB. For 8 GB VRAM use the 14.27 GB file (≈15.5 GB memory at 8 k context). For 16 GB VRAM use the 17.33 GB file (≈18.5 GB memory). Larger VRAM allows the 23.48 GB or 26.06 GB files with higher memory estimates. Estimates are approximate.
What GPU do you need for Qwopus3.6 35B A3B Coder APEX 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 the main file (14.3 GB file, about 15.5 GB in use).
- 24 GB VRAM: the best quant that fits is the main file (17.3 GB file, about 18.5 GB in use).
- 32 GB VRAM: the best quant that fits is the main file (26.1 GB file, about 27.2 GB in use).
Which Qwopus3.6 35B A3B Coder APEX MTP quant should you choose?
If memory is tight, the smallest file is the first one in the table at 14.3 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 Qwopus3.6 35B A3B Coder APEX MTP
How much VRAM does Qwopus3.6 35B A3B Coder APEX MTP need?
About 24.7 GB at its main file with an 8K context window. That is the 23.5 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 35B A3B Coder APEX MTP on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 15.5 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Qwopus3.6 35B A3B Coder APEX MTP GGUF?
It depends on the quant: file is 14.3 GB, file is 17.3 GB, file is 17.3 GB, file is 23.5 GB, file is 23.5 GB, file is 26.1 GB and 1 more.
What context length does Qwopus3.6 35B A3B Coder APEX 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 0.7 GB at 8K and 2.8 GB at 32K.
Where can I download Qwopus3.6 35B A3B Coder APEX MTP GGUF?
The files are on Hugging Face in the mudler/Qwopus3.6-35B-A3B-Coder-APEX-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 35B A3B Coder APEX 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.
Can I run this model on 8 GB VRAM?
Use the 14.27 GB GGUF file; it requires about 15.5 GB memory at 8 k context, which is close to 8 GB VRAM but may need swapping.
Does this model support vision tasks?
Yes, it includes a built‑in vision encoder (mmproj) bundled with the trunk.
What license applies to this model?
The model is released under the Apache‑2.0 license.