occamy 1.0 mtp needs about 2.4 GB of memory at Q4_K_M (a 1.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 3 quants, from 1.3 GB (Q4_K_M) to 3.7 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.8 GB.
Occamy 1.0 MTP – a compact agentic model for long‑horizon workflows
Occamy 1.0 MTP is a 1.86B parameter model built on the qwen35moe architecture. It is a mixture‑of‑experts model designed for sustained agentic tasks such as tool calling, coding and structured API use. The model is released under Apache‑2.0 and is available as GGUF files.
Good at
- Long‑horizon agentic workflows
- Tool calling and terminal coding
- Structured API interactions
Limits
- No vision support
- Requires a compatible Occamy 1.0 target model
- Experimental MTP head
Best for
- Co‑work automation
- Multi‑step professional workflows
- Tool‑driven code generation
Who it’s for. Developers and researchers building agentic applications that need persistent state and tool integration. The model is suitable for users who can run GGUFs in llama.cpp and have a compatible Occamy 1.0 base model.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 1.3 GB | 2.4 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 → |
For 8 GB VRAM, use Q4_K_M (1.26 GB, ~2.4 GB memory at 8k context). If 12 GB VRAM is available, Q8_0 (1.99 GB, ~3.2 GB memory) is a good balance. For larger budgets, BF16 (3.74 GB, ~4.9 GB memory) offers higher precision.
What GPU do you need for occamy 1.0 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: 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 occamy 1.0 mtp quant should you choose?
Q4_K_M is the usual starting point for occamy 1.0 mtp: it balances file size and quality well. Here it is a 1.3 GB file.
The Q8_0 file is 2.0 GB, about 1.6 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 occamy 1.0 mtp
How much VRAM does occamy 1.0 mtp need?
About 2.4 GB at Q4_K_M with an 8K context window. That is the 1.3 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 occamy 1.0 mtp 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 occamy 1.0 mtp GGUF?
It depends on the quant: Q4_K_M is 1.3 GB, Q8_0 is 2.0 GB, BF16 is 3.7 GB.
What context length does occamy 1.0 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 occamy 1.0 mtp GGUF?
The files are on Hugging Face in the moontato/occamy-1.0-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 occamy 1.0 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 Occamy 1.0 MTP on 8 GB VRAM?
Yes, the Q4_K_M quantization uses 1.26 GB and requires about 2.4 GB of VRAM at 8k context, which fits within 8 GB.
Do I need a separate vision projector?
No, Occamy 1.0 MTP does not support vision; it is a text‑only model.
Is the MTP head standalone?
No, it must be used together with a compatible Occamy 1.0 target model; it is not a standalone language model.