QW

Qwen3.5 35B A3B Sceptic v3.4

QwenGGUF by kataguruUpdated 2026-10-28
Download on Hugging Face
Parameters35.5B
Context256K
Layers41
Architectureqwen35moe
Smallest quant1.3 GB
Quick answer

Qwen3.5 35B A3B Sceptic v3.4 needs about 2.4 GB of memory at Q4_K_M (a 1.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 5 quants, from 1.3 GB (Q4_K_M) to 16.8 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 2.8 GB.

Qwen3.5 35B A3B Sceptic v3.4 – 35B parameter MoE model with vision and reasoning

Qwen3.5 35B A3B Sceptic v3.4 is a causal language model with a vision encoder. It contains 35.5B parameters, 3B active per token, and supports 262144 context tokens. The model is released under Apache‑2.0 and is available in several GGUF quantizations.

Good at

  • Reasoning
  • Vision understanding
  • Multilingual support

Limits

  • Requires 8‑k context for memory estimates
  • No built‑in vision support in llama.cpp
  • Large VRAM needed for full precision

Best for

  • Chatbots needing vision input
  • Multilingual content generation
  • AI research with MoE models

Who it’s for. Developers and researchers who need a large multimodal model with efficient Mixture‑of‑Experts inference. The model is suitable for environments that can handle the VRAM and context requirements.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M1.3 GB 2.4 GB
Fits Get file →
Q8_02.0 GB 3.2 GB
Fits Get file →
—13.0 GB 14.1 GB
Too big Get file →
—14.6 GB 15.8 GB
Too big Get file →
—16.8 GB 18.0 GB
Too big Get file →

For 8‑k context, the Q4_K_M quant (~1.26 GB) uses about 2.4 GB of memory, suitable for 8 GB VRAM. The Q8_0 quant (~1.99 GB) uses about 3.2 GB, fitting 12 GB VRAM. Larger 12.96 GB and 14.57 GB files need 14.1 GB and 15.8 GB memory respectively, suitable for 16 GB VRAM or more.

What GPU do you need for Qwen3.5 35B A3B Sceptic v3.4?

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 Q8_0 (2.0 GB file, about 3.2 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (2.0 GB file, about 3.2 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (2.0 GB file, about 3.2 GB in use).
  • 16 GB VRAM: the best quant that fits is the main file (14.6 GB file, about 15.8 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (16.8 GB file, about 18.0 GB in use).

Which Qwen3.5 35B A3B Sceptic v3.4 quant should you choose?

Q4_K_M is the usual starting point for Qwen3.5 35B A3B Sceptic v3.4: it balances file size and quality well. Here it is a 1.3 GB file.

The Q8_0 file is 2.0 GB, about 1.6 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

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 bykataguru
FamilyQwen
Licenseapache-2.0
Downloads (HF)1,929
Last updated2026-10-28

Frequently asked questions about Qwen3.5 35B A3B Sceptic v3.4

How much VRAM does Qwen3.5 35B A3B Sceptic v3.4 need?

About 2.4 GB at Q4_K_M with an 8K context window. That is the 1.3 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 Qwen3.5 35B A3B Sceptic v3.4 on an 8 GB GPU?

Yes, with Q8_0: the 2.0 GB file needs about 3.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Qwen3.5 35B A3B Sceptic v3.4 GGUF?

It depends on the quant: Q4_K_M is 1.3 GB, Q8_0 is 2.0 GB, file is 13.0 GB, file is 14.6 GB, file is 16.8 GB.

What context length does Qwen3.5 35B A3B Sceptic v3.4 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 Qwen3.5 35B A3B Sceptic v3.4 GGUF?

The files are on Hugging Face in the kataguru/Qwen3.5-35B-A3B-Sceptic-v3.4-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 Qwen3.5 35B A3B Sceptic v3.4 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 Qwen3.5 35B A3B Sceptic v3.4 on 8 GB VRAM?

The Q4_K_M quant uses about 2.4 GB at 8‑k context, so it fits 8 GB VRAM. Higher precision quants will exceed the limit.

Does the model support vision in llama.cpp?

Vision support is not built into llama.cpp; a separate vision adapter is required.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of Qwen3.5-35B-A3B

Similar models

Browse all →

More from kataguru

All by kataguru →

More Qwen models

All Qwen →

Other large models

All large models →