moziAI 35B A3B MOE MTP needs about 17.1 GB of memory at Q4_K_M (a 15.9 GB file) with an 8K context window, so it fits on a 24 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 2.8 GB.
MoziAI 35B A3B MOE MTP – a 35B‑parameter multimodal model with 3B active experts
MoziAI 35B A3B MOE MTP is a 35‑billion‑parameter mixture‑of‑experts model based on the Ornith family. It supports tools and vision and is released under the Apache‑2.0 license. The model is available in a single Q4_K_M quantized GGUF file of 15.87 GB.
Good at
- Vision and tool use
- Large context handling up to 262 144 tokens
- Mixture‑of‑experts efficiency
Limits
- Requires 8 k context for memory estimate
- No explicit vision or tool limits beyond context
- Only one quant available (Q4_K_M)
Best for
- Local multimodal inference on consumer GPUs
- Tool‑enabled agentic tasks
- Large‑context document analysis
Who it’s for. Developers and researchers needing a locally deployable multimodal model with a large context window and mixture‑of‑experts architecture. The model is suitable for applications that require vision and tool integration without cloud dependence.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 15.9 GB | 17.1 GB | Too big | Get file → |
The Q4_K_M quant file is 15.87 GB and needs about 17.1 GB of VRAM at 8 k context. For 8 GB VRAM use, the model cannot run. For 20 GB VRAM, the model fits comfortably. No other quants are provided, so use Q4_K_M for all deployments.
What GPU do you need for moziAI 35B A3B MOE MTP?
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 (15.9 GB file, about 17.1 GB in use).
Which moziAI 35B A3B MOE MTP quant should you choose?
Q4_K_M is the usual starting point for moziAI 35B A3B MOE MTP: it balances file size and quality well. Here it is a 15.9 GB file.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about moziAI 35B A3B MOE MTP
How much VRAM does moziAI 35B A3B MOE MTP need?
About 17.1 GB at Q4_K_M with an 8K context window. That is the 15.9 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 moziAI 35B A3B MOE MTP on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 17.1 GB, so you would need a larger GPU or CPU offloading.
What is the file size of moziAI 35B A3B MOE MTP GGUF?
It depends on the quant: Q4_K_M is 15.9 GB.
What context length does moziAI 35B A3B MOE MTP 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 moziAI 35B A3B MOE MTP GGUF?
The files are on Hugging Face in the chenyumo/moziAI-35B-A3B-MOE-MTP repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does moziAI 35B A3B MOE 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 MoziAI 35B A3B MOE MTP on 8 GB VRAM?
No. The Q4_K_M quant requires roughly 17 GB of VRAM at 8 k context, so 8 GB is insufficient.
Does the model support vision?
Yes, the model has detected vision ability and can process image inputs.
What license applies to this model?
The model is released under the Apache‑2.0 license, allowing free commercial use.