QW

Qwen3.6 35B A3B

QwenGGUF by lym00Updated 2026-06-17
Download on Hugging Face
Parameters1.86B
Context256K
Layers41
Architectureqwen35moe
Smallest quant1.2 GB
Quick answer

Qwen3.6 35B A3B needs about 3.2 GB of memory at Q8_0 (a 2.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 1.2 GB (Q4_0) to 3.7 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.8 GB.

Qwen3.6 35B A3B MTP GGUF for llama.cpp

Qwen3.6 35B A3B is a 1.86B parameter model with 3 active parameters in a mixture of experts. It supports reasoning and tools. The GGUF files are optimized for Multi-Token Prediction (MTP).

Good at

  • Reasoning
  • Tools usage
  • MTP inference

Limits

  • No vision support
  • Requires large VRAM for full context
  • Apache-2.0 license

Best for

  • MTP-based text generation
  • Tool-assisted workflows
  • Low-latency inference on GPU

Who it’s for. Developers building custom LLM applications with llama.cpp who need MTP support and moderate parameter count. The model is suitable for projects requiring reasoning and tool integration without vision capabilities.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_01.2 GB 2.4 GB
Fits Get file →
Q8_02.0 GB 3.2 GB
Fits Get file →
BF163.7 GB 4.9 GB
Fits Get file →
F163.7 GB 4.9 GB
Fits Get file →

For 8 GB VRAM use Q4_0 (1.19 GB file, ~2.4 GB memory). For 12 GB VRAM use Q8_0 (1.99 GB file, ~3.2 GB memory). For higher precision and more VRAM use BF16 or F16 (3.73 GB file, ~4.9 GB memory).

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

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: the best quant that fits is Q8_0 (2.0 GB file, about 3.2 GB in use).
  • 6 GB VRAM: the best quant that fits is BF16 (3.7 GB file, about 4.9 GB in use).

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

Q8_0 (2.0 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

If memory is tight, the smallest file is Q4_0 at 1.2 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35moe
Parameters1.86B (approximate, mixture of experts)
Active parameters3B
Layers41
Trained context262,144 tokens
KV cache (fp16)82 KB per token

Source

Quantized bylym00
FamilyQwen
Licenseapache-2.0
Downloads (HF)940
Last updated2026-06-17

Frequently asked questions about Qwen3.6 35B A3B

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

About 3.2 GB at Q8_0 with an 8K context window. That is the 2.0 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 on an 8 GB GPU?

Yes, with BF16: the 3.7 GB file needs about 4.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

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

It depends on the quant: Q4_0 is 1.2 GB, Q8_0 is 2.0 GB, BF16 is 3.7 GB, F16 is 3.7 GB.

What context length does Qwen3.6 35B A3B 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 35B A3B GGUF?

The files are on Hugging Face in the lym00/Qwen3.6-35B-A3B-MTP-ONLY-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 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 35B A3B on 8 GB VRAM?

Yes, using the Q4_0 quantized file which requires approximately 2.4 GB VRAM at 8k context.

Does this model support vision tasks?

No, the model does not include vision capabilities.

What license applies to this model?

The model is released under the apache-2.0 license.

Similar models

Browse all →

More from lym00

All by lym00 →

More Qwen models

All Qwen →

Other tiny models

All tiny models →