QW

Qwopus3.6 35B A3B v1 APEX MTP

QwopusGGUF by mudlerUpdated 2026-08-17
Download on Hugging Face
Parameters35.5B
Context256K
Layers41
Architectureqwen35moe
Smallest quant11.7 GB
Quick answer

Qwopus3.6 35B A3B v1 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 9 quants, from 11.7 GB to 71.1 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.8 GB.

Qwopus3.6 35B A3B v1 APEX MTP – a 35.5B parameter MoE model with 262k context window

Qwopus3.6 35B A3B v1 APEX MTP is a 35.5B parameter mixture‑of‑experts model based on Qwen3.6-35B-A3B. It supports a 262,144 token context window and includes a bundled MTP head for self‑speculative decoding. The model is released under the apache‑2.0 license.

Good at

  • Large‑context reasoning
  • Self‑speculative decoding
  • Mixture‑of‑experts efficiency

Limits

  • No vision support without mmproj.gguf
  • Requires high VRAM for full precision
  • Experimental release, no safety testing

Best for

  • Agentic coding tasks
  • Deep reasoning workflows
  • Multimodal research with vision enabled

Who it’s for. Researchers and developers who need a high‑capacity MoE model with a massive context window and are comfortable working with experimental releases. The model is suitable for advanced LLM research and prototyping of agentic systems.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—11.7 GB 12.9 GB
Too big Get file →
—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 →
F1671.1 GB 72.3 GB
Too big Get file →

For 8–16 GB VRAM, use the smallest unknown quant file (11.69 GB, 12.9 GB memory). For 16–32 GB VRAM, the 17.33 GB unknown quant (18.5 GB memory) is appropriate. For 32–64 GB VRAM, the 23.48 GB unknown quant (24.7 GB memory) or the 26.06 GB unknown quant (27.2 GB memory) can be used. Full‑precision F16 requires 71.07 GB file and 72.3 GB memory.

What GPU do you need for Qwopus3.6 35B A3B v1 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).
  • 48 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 v1 APEX MTP quant should you choose?

If memory is tight, the smallest file is the first one in the table at 11.7 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

Architectureqwen35moe
Parameters35.5B (approximate, mixture of experts)
Active parameters3B
Layers41
Trained context262,144 tokens
KV cache (fp16)82 KB per token

Source

Quantized bymudler
FamilyQwopus
Licenseapache-2.0
Downloads (HF)2,333
Last updated2026-08-17

Frequently asked questions about Qwopus3.6 35B A3B v1 APEX MTP

How much VRAM does Qwopus3.6 35B A3B v1 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 v1 APEX MTP on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 12.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Qwopus3.6 35B A3B v1 APEX MTP GGUF?

It depends on the quant: file is 11.7 GB, 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 and 3 more.

What context length does Qwopus3.6 35B A3B v1 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 v1 APEX MTP GGUF?

The files are on Hugging Face in the mudler/Qwopus3.6-35B-A3B-v1-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 v1 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?

No, the smallest unknown quant requires 12.9 GB memory at 8k context, which exceeds 8 GB VRAM.

Does the model support vision?

Vision support is available only if the mmproj.gguf file is placed in the same directory as the main .gguf file.

Is the model safe for production use?

The release is experimental and has not undergone complete safety testing; it is intended for research and exploration.

Other GGUFs of Qwopus3.6-35B-A3B-v1

Similar models

Browse all →

More from mudler

All by mudler →

More Qwopus models

All Qwopus →

Other large models

All large models →