Clef Artemis needs about 15.4 GB of memory at Q3_K_M (a 12.7 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 5 quants, from 10.5 GB (Q2_K) to 14.8 GB (IQ4_XS). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.
Clef Artemis 27B decision model for typed question answering
Clef Artemis is a 27B multimodal decision model that returns probabilities for typed questions. It accepts text, JSON, images, or video as state and outputs one logit per option. The model is converted to GGUF for llama.cpp usage.
Good at
- Typed decision answering
- Multimodal input handling
- Probability outputs per option
Limits
- No free‑form text generation
- Requires llama.cpp runtime
- Large VRAM needed for full precision
Best for
- Decision‑making pipelines
- Batch classification tasks
- Local inference with privacy
Who it’s for. Developers needing a lightweight decision model that can run locally on a GPU. The model is useful for applications that require fast, probabilistic answers without text generation.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 10.5 GB | 13.1 GB | Too big | Get file → | |
| IQ3_XXS | 11.5 GB | 14.2 GB | Too big | Get file → | |
| Q3_K_M | 12.7 GB | 15.4 GB | Too big | Get file → | |
| IQ3_M | 14.3 GB | 17.0 GB | Too big | Get file → | |
| IQ4_XS | 14.8 GB | 17.5 GB | Too big | Get file → |
For 8 GB VRAM, use the Q2_K quant (10.49 GB file, ~13.1 GB memory at 8 k context). For 12 GB VRAM, Q3_K_M (12.72 GB file, ~15.4 GB memory). For 16 GB VRAM, IQ4_XS (14.82 GB file, ~17.5 GB memory). Estimates are approximate.
What GPU do you need for Clef 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: the best quant that fits is Q3_K_M (12.7 GB file, about 15.4 GB in use).
- 24 GB VRAM: the best quant that fits is IQ4_XS (14.8 GB file, about 17.5 GB in use).
Which Clef Artemis quant should you choose?
Q3_K_M (12.7 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.
If memory is tight, the smallest file is Q2_K at 10.5 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Clef Artemis
How much VRAM does Clef Artemis need?
About 15.4 GB at Q3_K_M with an 8K context window. That is the 12.7 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 Clef Artemis on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 13.1 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Clef Artemis GGUF?
It depends on the quant: Q2_K is 10.5 GB, IQ3_XXS is 11.5 GB, Q3_K_M is 12.7 GB, IQ3_M is 14.3 GB, IQ4_XS is 14.8 GB.
What context length does Clef 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 Clef Artemis GGUF?
The files are on Hugging Face in the turintech/Clef-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 Clef 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 Clef Artemis on 8 GB VRAM?
Use the Q2_K quant file (10.49 GB). It requires about 13.1 GB memory at 8 k context, so 8 GB VRAM is insufficient for full inference.
Does Clef Artemis support image inputs?
Yes, it accepts images via the vision projector from ggml-org/Clef-GGUF. Video frames can also be processed.
What license applies to Clef Artemis?
The model is released under the apache-2.0 license.