MTP Qwen3.6 35B A3B needs about 2.8 GB of memory at Q4_K_M (a 1.6 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 1.6 GB (Q4_K_M) to 3.7 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.8 GB.
MTP Qwen3.6 35B A3B – a mixture‑of‑experts language model in GGUF format
MTP Qwen3.6 35B A3B is a 1.86 billion‑parameter causal language model with 3 billion active parameters. It is trained on 262 144 context tokens and supports reasoning and tools. The GGUF files are designed to be used with the matching base model.
Good at
- Reasoning
- Tools usage
- Agentic coding
Limits
- Requires matching base model
- No standalone vision support
- Large VRAM needed for higher precision
Best for
- Developer tooling
- Coding assistance
- Iterative design
Who it’s for. Engineers and researchers who need a lightweight, open‑weight variant of Qwen3.6 for integration into custom inference pipelines. The model is suitable for projects that can provide the full base model and have sufficient GPU memory.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 1.6 GB | 2.8 GB | Fits | Get file → | |
| Q8_0 | 2.0 GB | 3.2 GB | Fits | Get file → | |
| BF16 | 3.7 GB | 4.9 GB | Fits | Get file → | |
| F16 | 3.7 GB | 4.9 GB | Fits | Get file → |
For 8 GB VRAM, use the Q4_K_M quant (file size 1.62 GB, estimated 2.8 GB memory at 8 k context). If more memory is available, Q8_0 (1.99 GB, 3.2 GB memory) offers higher precision. BF16 and F16 (3.74 GB, 4.9 GB memory) require larger GPUs.
What GPU do you need for MTP 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 MTP Qwen3.6 35B A3B quant should you choose?
Q4_K_M is the usual starting point for MTP Qwen3.6 35B A3B: it balances file size and quality well. Here it is a 1.6 GB file.
The Q8_0 file is 2.0 GB, about 1.2 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
Source
Frequently asked questions about MTP Qwen3.6 35B A3B
How much VRAM does MTP Qwen3.6 35B A3B need?
About 2.8 GB at Q4_K_M with an 8K context window. That is the 1.6 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 MTP 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 MTP Qwen3.6 35B A3B GGUF?
It depends on the quant: Q4_K_M is 1.6 GB, Q8_0 is 2.0 GB, BF16 is 3.7 GB, F16 is 3.7 GB.
What context length does MTP 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 MTP Qwen3.6 35B A3B GGUF?
The files are on Hugging Face in the tomngdev/MTP-Qwen3.6-35B-A3B-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 MTP 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 this model on 8 GB VRAM?
Yes, the Q4_K_M quant uses about 2.8 GB of VRAM at 8 k context, which fits within 8 GB. The Q8_0 quant uses about 3.2 GB.
Is the GGUF file usable on its own?
No, the GGUF files are not standalone. They must be used with the matching base model GGUF.
What license does this model use?
The model is licensed under apache-2.0, following the original base model license.