Qwen3.6 35B A3B MTP needs about 26.5 GB of memory at Q4_K_XL (a 23.3 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 7 quants, from 0.9 GB to 39.3 GB (Q8_K_XL).
Qwen3.6 35B A3B MTP – a 35B causal language model with multi‑token prediction
Qwen3.6 35B A3B MTP is a causal language model built on the Qwen3.6 architecture. It contains 35B total parameters with 3B active experts and supports a native context length of 262,144 tokens, extensible to 1,010,000 tokens. The model is released under the Apache‑2.0 license.
Good at
- Agentic coding with frontend workflows
- Multi‑step reasoning preservation
- Large context handling
Limits
- Requires custom llama.cpp build for MTP
- No vision support
- Large VRAM needed for higher quantizations
Best for
- Developers building coding assistants
- Researchers needing long‑context generation
- Teams deploying on GPU‑rich servers
Who it’s for. The model is intended for developers and researchers who need a large, multi‑expert language model with extended context and multi‑token prediction capabilities. It is suitable for applications that can accommodate the memory and software requirements described.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.9 GB | 1.5 GB | Fits | Get file → | |
| Q2_K_XL | 13.2 GB | 15.3 GB | Too big | Get file → | |
| Q3_K_XL | 17.7 GB | 20.4 GB | Too big | Get file → | |
| Q4_K_XL | 23.3 GB | 26.5 GB | Too big | Get file → | |
| Q5_K_XL | 27.5 GB | 31.3 GB | Too big | Get file → | |
| Q6_K_XL | 32.7 GB | 37.2 GB | Too big | Get file → | |
| Q8_K_XL | 39.3 GB | 44.6 GB | Too big | Get file → |
For 8 GB VRAM, use Q2_K_XL (file size 13.19 GB, ~15.3 GB memory at 8 k context). For 16 GB VRAM, Q3_K_XL (17.74 GB, ~20.4 GB memory) is a good balance. For 32 GB VRAM, Q4_K_XL (23.26 GB, ~26.5 GB memory) provides higher quality while staying within budget. Memory estimates are approximate.
What GPU do you need for Qwen3.6 35B A3B MTP?
These figures add the file size, an fp16 KV cache at an 8K context window 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 the main file (0.9 GB file, about 1.5 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.9 GB file, about 1.5 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.9 GB file, about 1.5 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (0.9 GB file, about 1.5 GB in use).
- 16 GB VRAM: the best quant that fits is Q2_K_XL (13.2 GB file, about 15.3 GB in use).
- 24 GB VRAM: the best quant that fits is Q3_K_XL (17.7 GB file, about 20.4 GB in use).
- 32 GB VRAM: the best quant that fits is Q5_K_XL (27.5 GB file, about 31.3 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_K_XL (39.3 GB file, about 44.6 GB in use).
Which Qwen3.6 35B A3B MTP quant should you choose?
Q4_K_XL (23.3 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.
If memory is tight, the smallest file is the first one in the table at 0.9 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Qwen3.6 35B A3B MTP
How much VRAM does Qwen3.6 35B A3B MTP need?
About 26.5 GB at Q4_K_XL with an 8K context window. That is the 23.3 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 Qwen3.6 35B A3B MTP on an 8 GB GPU?
Yes, with the smaller files: the 0.9 GB file needs about 1.5 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 MTP GGUF?
It depends on the quant: file is 0.9 GB, Q2_K_XL is 13.2 GB, Q3_K_XL is 17.7 GB, Q4_K_XL is 23.3 GB, Q5_K_XL is 27.5 GB, Q6_K_XL is 32.7 GB and 1 more.
What context length does Qwen3.6 35B A3B MTP support?
The GGUF header lists a trained context length of 262,144 tokens (256K).
Where can I download Qwen3.6 35B A3B MTP GGUF?
The files are on Hugging Face in the havenoammo/Qwen3.6-35B-A3B-MTP-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 MTP 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 MTP on 8 GB VRAM?
Only the Q2_K_XL quantization will fit, using about 15.3 GB of VRAM at 8 k context. Higher quantizations exceed 8 GB.
Does this model support vision tasks?
No, the model is a causal language model and does not include a vision encoder.
What license applies to this model?
The model is released under the Apache‑2.0 license.