Qwen3.5 35B A3B Heretic needs about 22.3 GB of memory at Q4_K_M (a 21.2 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 5 quants, from 16.8 GB (Q3_K_M) to 36.9 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.
Qwen3.5 35B A3B Heretic – 35B total, 3B active, multimodal
Qwen3.5 35B A3B Heretic is a mixture‑of‑experts model with 35B total parameters and 3B active parameters per token. It supports reasoning, tools, and vision. The model is trained on 262144 context tokens and released under the apache-2.0 license.
Good at
- Reasoning
- Vision understanding
- Tool usage
Limits
- Requires large VRAM for higher quality quants
- No dedicated vision API, uses multimodal projector
- License is apache-2.0
Best for
- Multimodal inference on high‑end GPUs
- Research on MoE architectures
- Deploying vision‑language agents
Who it’s for. Developers needing a large multimodal model with active‑parameter efficiency. Researchers exploring mixture‑of‑experts and vision‑language tasks. Enterprises deploying on GPUs with sufficient VRAM.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_M | 16.8 GB | 17.9 GB | Too big | Get file → | |
| Q4_K_M | 21.2 GB | 22.3 GB | Too big | Get file → | |
| Q5_K_M | 24.8 GB | 25.9 GB | Too big | Get file → | |
| Q6_K | 28.5 GB | 29.7 GB | Too big | Get file → | |
| Q8_0 | 36.9 GB | 38.1 GB | Too big | Get file → |
For 16 GB VRAM, use Q3_K_M (file size 16.76 GB, estimated 17.9 GB memory). For 24 GB VRAM, Q5_K_M (24.76 GB, 25.9 GB). For 32 GB VRAM, Q6_K (28.51 GB, 29.7 GB). For 36 GB VRAM, Q8_0 (36.9 GB, 38.1 GB).
What GPU do you need for Qwen3.5 35B A3B Heretic?
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 (21.2 GB file, about 22.3 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (28.5 GB file, about 29.7 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (36.9 GB file, about 38.1 GB in use).
Which Qwen3.5 35B A3B Heretic quant should you choose?
Q4_K_M is the usual starting point for Qwen3.5 35B A3B Heretic: it balances file size and quality well. Here it is a 21.2 GB file.
The Q8_0 file is 36.9 GB, about 1.7 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.
If memory is tight, the smallest file is Q3_K_M at 16.8 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
Source
Frequently asked questions about Qwen3.5 35B A3B Heretic
How much VRAM does Qwen3.5 35B A3B Heretic need?
About 22.3 GB at Q4_K_M with an 8K context window. That is the 21.2 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 Heretic on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 17.9 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Qwen3.5 35B A3B Heretic GGUF?
It depends on the quant: Q3_K_M is 16.8 GB, Q4_K_M is 21.2 GB, Q5_K_M is 24.8 GB, Q6_K is 28.5 GB, Q8_0 is 36.9 GB.
What context length does Qwen3.5 35B A3B Heretic 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 Qwen3.5 35B A3B Heretic GGUF?
The files are on Hugging Face in the alexdenton/Qwen3.5-35B-A3B-heretic-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 Heretic 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 Heretic on a single RTX 3090?
Yes, with the Q5_K_M quantization it fits on a 24 GB RTX 3090, leaving room for context.
What VRAM is needed for the best quality quantization?
The Q8_0 quantization requires about 38.1 GB VRAM, suitable for dual RTX 3090 setups.
Does the model support vision tasks?
Yes, it includes a multimodal projector for vision understanding.