POCKET-Darwin-180B needs about 112.6 GB of memory at Q4_K_XL (a 111.3 GB file) with an 8K context window, which is more than a 48 GB GPU holds. Longer context needs more: at 32K tokens the KV cache alone adds about 3.2 GB.
180B Mixture‑of‑Experts model, 4‑bit GGUF, runs on laptops and servers
POCKET‑Darwin‑180B is a 180 B MoE model quantized to Q4_K_XL. The 111.33 GB GGUF file is split into four shards. It supports 262 144‑token context and can run on a laptop with an 8 GB GPU and 32 GB RAM or on a CPU‑only server.
Good at
- Large‑context reasoning
- Vision‑language tasks
- Self‑improvement capabilities
Limits
- Requires 111 GB GGUF file
- Runs only with Q4_K_XL quant
- No vision support in llama.cpp
Best for
- Running on personal laptops
- CPU‑only inference on servers
- Mini‑PC deployments with 128 GB RAM
Who it’s for. Engineers and researchers who need a 180 B MoE model on limited hardware. The model is suitable for developers wanting to test large‑context reasoning and vision‑language tasks locally.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_XL | 111.3 GB (4 parts) | 112.6 GB | Too big | Get file → |
The only available quant is Q4_K_XL, 111.33 GB. For 8 GB GPU use the 4‑shard file; the model will use ~112.6 GB VRAM at 8 k context. If memory is constrained, consider a CPU‑only run with 78.8 GB peak RAM.
What GPU do you need for POCKET-Darwin-180B?
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: no quant fits at an 8K context.
- 32 GB VRAM: no quant fits at an 8K context.
- 48 GB VRAM: no quant fits at an 8K context.
Which POCKET-Darwin-180B quant should you choose?
Q4_K_XL (111.3 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about POCKET-Darwin-180B
How much VRAM does POCKET-Darwin-180B need?
About 112.6 GB at Q4_K_XL with an 8K context window. That is the 111.3 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 POCKET-Darwin-180B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 112.6 GB, so you would need a larger GPU or CPU offloading.
What is the file size of POCKET-Darwin-180B GGUF?
It depends on the quant: Q4_K_XL is 111.3 GB.
What context length does POCKET-Darwin-180B 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 3.2 GB at 32K.
Where can I download POCKET-Darwin-180B GGUF?
The files are on Hugging Face in the FINAL-Bench/POCKET-Darwin-180B-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 POCKET-Darwin-180B use?
Hugging Face lists the license as other. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Does the model support vision tasks in llama.cpp?
No, the current GGUF build does not include vision support in llama.cpp.
What is the context length of this model?
The model supports a 262,144‑token context length.