Qwen3.5 35B A3B Sceptic v3 1M needs about 22.9 GB of memory at Q4_K_M (a 21.7 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 5 quants, from 15.5 GB (Q3_K_S) to 29.2 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 2.8 GB.
Qwen3.5 35B A3B Sceptic v3 1M – 35B‑parameter MoE model with 1M context
Qwen3.5 35B A3B Sceptic v3 1M is a 35.5B‑parameter mixture‑of‑experts model with 1,048,576 token context. It supports reasoning, tools and vision. The model is released under apache‑2.0 and is available in multiple GGUF quantisations.
Good at
- Large‑context reasoning
- Vision and OCR multimodality
- Multi‑token prediction decoding
Limits
- No vision support in llama.cpp without Qwen3VL‑visio
- Requires 1M context metadata
- Large VRAM needed for higher quants
Best for
- Local inference on workstations
- Fine‑tuning with 1M context
- Multimodal applications with Qwen3VL‑visio
Who it’s for. Developers and researchers needing a 1M‑token context model for reasoning, tools and vision tasks. The model is suitable for local deployment in LM Studio, llama.cpp or Ollama.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_S | 15.5 GB | 16.7 GB | Too big | Get file → | |
| Q3_K_M | 17.2 GB | 18.4 GB | Too big | Get file → | |
| Q4_K_M | 21.7 GB | 22.9 GB | Too big | Get file → | |
| Q5_K_M | 25.3 GB | 26.5 GB | Too big | Get file → | |
| Q6_K | 29.2 GB | 30.4 GB | Too big | Get file → |
For 8 GB VRAM, use Q3_K_S (15.55 GB file, 16.7 GB memory at 8k context). For 16 GB VRAM, Q4_K_M (21.71 GB file, 22.9 GB memory) is recommended. For 32 GB VRAM, Q5_K_M or Q6_K can be used, but memory usage will be higher.
What GPU do you need for Qwen3.5 35B A3B Sceptic v3 1M?
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: no quant fits at an 8K context.
- 24 GB VRAM: the best quant that fits is Q4_K_M (21.7 GB file, about 22.9 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (29.2 GB file, about 30.4 GB in use).
Which Qwen3.5 35B A3B Sceptic v3 1M quant should you choose?
Q4_K_M is the usual starting point for Qwen3.5 35B A3B Sceptic v3 1M: it balances file size and quality well. Here it is a 21.7 GB file.
If memory is tight, the smallest file is Q3_K_S at 15.5 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about Qwen3.5 35B A3B Sceptic v3 1M
How much VRAM does Qwen3.5 35B A3B Sceptic v3 1M need?
About 22.9 GB at Q4_K_M with an 8K context window. That is the 21.7 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 1M on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 16.7 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Qwen3.5 35B A3B Sceptic v3 1M GGUF?
It depends on the quant: Q3_K_S is 15.5 GB, Q3_K_M is 17.2 GB, Q4_K_M is 21.7 GB, Q5_K_M is 25.3 GB, Q6_K is 29.2 GB.
What context length does Qwen3.5 35B A3B Sceptic v3 1M support?
The GGUF header lists a trained context length of 1,048,576 tokens (1024K). 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 1M GGUF?
The files are on Hugging Face in the kataguru/Qwen3.5-35B-A3B-Sceptic-v3-1M-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 1M 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 1M on 8 GB VRAM?
The smallest quant, Q3_K_S, requires 16.7 GB memory at 8k context, so 8 GB VRAM is insufficient.
Does the model support vision in llama.cpp?
Vision is supported only with the Qwen3VL‑visio multimodality, which is not included in the provided GGUF files.
What context length does the model support?
The model supports 1,048,576 tokens, as specified in the GGUF metadata.