QW

Qwen3.6 35B A3B tq

QwenGGUF by mad-lab-aiUpdated 2026-04-16
Download on Hugging Face
Parameters34.7B
Context256K
Layers40
Architectureqwen35moe
Smallest quant7.9 GB
Quick answer

Qwen3.6 35B A3B tq needs about 10.6 GB of memory at TQ2_0 (a 9.5 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 4 quants, from 7.9 GB (TQ1_0) to 21.8 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.

Qwen3.6 35B A3B TurboQuant GGUF – 35B total, 3B active per token

Qwen3.6 35B A3B TurboQuant is a causal language model with a mixture‑of‑experts architecture. It contains 35.7B total parameters, but only 3B are active for each token. The model supports reasoning and tool usage.

Good at

  • Reasoning tasks
  • Tool‑based interactions
  • Code generation

Limits

  • No vision support
  • Large memory requirement for high context
  • Requires Apache‑2.0 license

Best for

  • Developers needing efficient local inference
  • Researchers testing MoE behavior
  • Applications with limited GPU memory

Who it’s for. This model is suitable for developers and researchers who want a large‑scale language model that can be run locally with CPU offloading. It is ideal for those who need reasoning and tool‑use capabilities without a vision encoder.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
TQ1_07.9 GB 9.1 GB
Too big Get file →
TQ2_09.5 GB 10.6 GB
Too big Get file →
—17.6 GB 18.8 GB
Too big Get file →
—21.8 GB 23.0 GB
Too big Get file →

For 8 GB VRAM use the TQ1_0 quant (7.9 GB file, ~9.1 GB memory at 8 k context). For 12 GB VRAM use TQ2_0 (9.47 GB file, ~10.6 GB memory). Larger VRAM allows the unknown quants (17.58 GB and 21.85 GB).

What GPU do you need for Qwen3.6 35B A3B tq?

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 TQ2_0 (9.5 GB file, about 10.6 GB in use).
  • 16 GB VRAM: the best quant that fits is TQ2_0 (9.5 GB file, about 10.6 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (21.8 GB file, about 23.0 GB in use).

Which Qwen3.6 35B A3B tq quant should you choose?

TQ2_0 (9.5 GB) is the middle option in this repository. Lower bit counts mean smaller files and more quality loss.

If memory is tight, the smallest file is TQ1_0 at 7.9 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

Architectureqwen35moe
Parameters34.7B (approximate, mixture of experts)
Active parameters3B
Layers40
Trained context262,144 tokens
KV cache (fp16)80 KB per token

Source

Quantized bymad-lab-ai
FamilyQwen
Licenseapache-2.0
Downloads (HF)589
Last updated2026-04-16

Frequently asked questions about Qwen3.6 35B A3B tq

How much VRAM does Qwen3.6 35B A3B tq need?

About 10.6 GB at TQ2_0 with an 8K context window. That is the 9.5 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 Qwen3.6 35B A3B tq on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Qwen3.6 35B A3B tq GGUF?

It depends on the quant: TQ1_0 is 7.9 GB, TQ2_0 is 9.5 GB, file is 17.6 GB, file is 21.8 GB.

What context length does Qwen3.6 35B A3B tq 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 2.7 GB at 32K.

Where can I download Qwen3.6 35B A3B tq GGUF?

The files are on Hugging Face in the mad-lab-ai/Qwen3.6-35B-A3B-tq-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 35B A3B tq 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?

Yes, the TQ1_0 quant is 7.9 GB and requires about 9.1 GB of VRAM at 8 k context.

Does this model support vision tasks?

No, the model is a language model only and does not include a vision encoder.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of Qwen3.6-35B-A3B

Similar models

Browse all →

More from mad-lab-ai

All by mad-lab-ai →

More Qwen models

All Qwen →

Other large models

All large models →