MTP Qwen3.5 122B A10B needs about 4.5 GB of memory at Q4_K_M (a 3.2 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 4 quants, from 3.2 GB (Q4_K_M) to 8.1 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.3 GB.
MTP Qwen3.5 122B A10B – a Mixture‑of‑Experts model for advanced reasoning and tool use
MTP Qwen3.5 122B A10B is a 122B parameter model with 10B active experts. It supports reasoning and tool usage and is optimized for speculative decoding. The model is released under the Apache‑2.0 license.
Good at
- Reasoning tasks
- Tool‑based interactions
- Large context handling
Limits
- Requires matching base model
- No standalone use
- Large VRAM needed for full precision
Best for
- Complex question answering
- Automated agent workflows
- Research prototyping
Who it’s for. Developers and researchers needing a high‑capacity language model with expert routing. The model is suitable for applications that can leverage its reasoning and tool‑use abilities and have sufficient GPU memory.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 3.2 GB | 4.5 GB | Fits | Get file → | |
| Q8_0 | 4.3 GB | 5.6 GB | Fits | Get file → | |
| BF16 | 8.1 GB | 9.4 GB | Too big | Get file → | |
| F16 | 8.1 GB | 9.4 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (3.21 GB, 4.5 GB memory at 8 k context). For 12 GB VRAM, Q8_0 (4.32 GB, 5.6 GB memory). For 24 GB VRAM, BF16 or F16 (8.11 GB, 9.4 GB memory). Estimates are approximate.
What GPU do you need for MTP Qwen3.5 122B A10B?
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: the best quant that fits is Q8_0 (4.3 GB file, about 5.6 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (4.3 GB file, about 5.6 GB in use).
- 12 GB VRAM: the best quant that fits is BF16 (8.1 GB file, about 9.4 GB in use).
Which MTP Qwen3.5 122B A10B quant should you choose?
Q4_K_M is the usual starting point for MTP Qwen3.5 122B A10B: it balances file size and quality well. Here it is a 3.2 GB file.
The Q8_0 file is 4.3 GB, about 1.3 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 Qwen3.5 122B A10B
How much VRAM does MTP Qwen3.5 122B A10B need?
About 4.5 GB at Q4_K_M with an 8K context window. That is the 3.2 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 MTP Qwen3.5 122B A10B on an 8 GB GPU?
Yes, with Q8_0: the 4.3 GB file needs about 5.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of MTP Qwen3.5 122B A10B GGUF?
It depends on the quant: Q4_K_M is 3.2 GB, Q8_0 is 4.3 GB, BF16 is 8.1 GB, F16 is 8.1 GB.
What context length does MTP Qwen3.5 122B A10B support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.8 GB at 8K and 3.3 GB at 32K.
Where can I download MTP Qwen3.5 122B A10B GGUF?
The files are on Hugging Face in the tomngdev/MTP-Qwen3.5-122B-A10B-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 Qwen3.5 122B A10B 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 MTP Qwen3.5 122B A10B on 8 GB VRAM?
Yes, using the Q4_K_M quant which requires about 4.5 GB memory at 8 k context.
Do I need the base model to use this GGUF?
Yes, the GGUF files are only the MTP component and must be paired with the matching base model.
What license applies to this model?
The model is licensed under Apache‑2.0, following the base model license.