pplx decider 27B Artemis needs about 16.9 GB of memory at IQ3_M (a 14.3 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 2 quants, from 14.3 GB (IQ3_M) to 15.3 GB (Q4_K_S). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.
pplx decider 27B Artemis – decision‑making LLM with vision support
pplx decider 27B Artemis is a 26.9B‑parameter decision model built on Qwen3.5. It supports reasoning, tools, and vision, delivering typed answers with probability in a single pass. The model is optimized for low‑latency inference on a 24 GB GPU.
Good at
- reasoning
- tools
- vision
Limits
- no chat endpoint
- requires llama.cpp 9 Oct 2026 or newer
- peak GPU memory 18.9 GiB with images
Best for
- typed decision tasks
- image‑based decision queries
- low‑latency inference on 24 GB GPU
Who it’s for. Developers building decision‑oriented applications that need a typed answer with probability. Suitable for systems that can send requests to llama‑server’s /v1/systemone endpoint.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ3_M | 14.3 GB | 16.9 GB | Too big | Get file → | |
| Q4_K_S | 15.3 GB | 17.9 GB | Too big | Get file → |
The Q4_K_S quant (15.28 GB) uses about 17.9 GB of VRAM at 8 k context and is recommended for most users. The IQ3_M quant (14.27 GB) uses about 16.9 GB of VRAM at 8 k context and is a smaller alternative. Both are approximate estimates.
What GPU do you need for pplx decider 27B Artemis?
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_S (15.3 GB file, about 17.9 GB in use).
Which pplx decider 27B Artemis quant should you choose?
IQ3_M (14.3 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about pplx decider 27B Artemis
How much VRAM does pplx decider 27B Artemis need?
About 16.9 GB at IQ3_M with an 8K context window. That is the 14.3 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 pplx decider 27B Artemis on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 16.9 GB, so you would need a larger GPU or CPU offloading.
What is the file size of pplx decider 27B Artemis GGUF?
It depends on the quant: IQ3_M is 14.3 GB, Q4_K_S is 15.3 GB.
What context length does pplx decider 27B Artemis support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.6 GB at 32K.
Where can I download pplx decider 27B Artemis GGUF?
The files are on Hugging Face in the turintech/pplx-decider-27B-Artemis-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 pplx decider 27B Artemis 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 it on a 24 GB GPU?
Yes. Peak memory is 16.6 GiB for text and 18.9 GiB with images, fitting within 24 GB.
Does it support vision?
Yes, vision is enabled via the decision head and works with image inputs.
What llama.cpp version is required?
It requires llama.cpp 9 October 2026 or newer.