Clef needs about 19.2 GB of memory at Q4_K_M (a 16.5 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 10 quants, from 7.6 GB (IQ1_M) to 28.6 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.
27B multimodal decision model for structured queries
Clef is a 27B multimodal model that processes text, JSON, images, or video and returns probabilities for each option in a single forward pass. It has no free‑form text generation and is post‑trained from Qwen3.8‑27B. The model is licensed under Apache‑2.0.
Good at
- Decision making from multimodal input
- Fast single‑pass probability outputs
- No text generation required
Limits
- No free‑form text generation
- Requires multimodal projector for image/video
- Large VRAM needed for full precision
Best for
- Automated decision systems
- Structured question answering
- Workflow orchestration
Who it’s for. Developers building decision‑making services that need reliable probability outputs from text, images, or video. The model is suitable for backend services that integrate with Jev or SystemOne APIs.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_M | 7.6 GB | 10.3 GB | Too big | Get file → | |
| IQ2_M | 10.0 GB | 12.7 GB | Too big | Get file → | |
| Q2_K | 10.7 GB | 13.4 GB | Too big | Get file → | |
| IQ3_M | 12.6 GB | 15.2 GB | Too big | Get file → | |
| Q3_K_M | 13.3 GB | 15.9 GB | Too big | Get file → | |
| Q4_0 | 15.5 GB | 18.1 GB | Too big | Get file → | |
| Q4_K_M | 16.5 GB | 19.2 GB | Too big | Get file → | |
| Q5_K_M | 19.2 GB | 21.9 GB | Too big | Get file → | |
| Q6_K | 22.1 GB | 24.7 GB | Too big | Get file → | |
| Q8_0 | 28.6 GB | 31.2 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_M (7.63 GB, ~10.3 GB memory at 8 k context). For 12 GB VRAM, IQ2_M (10 GB, ~12.7 GB memory) is suitable. Larger budgets can use Q2_K or higher quantizations for better accuracy.
What GPU do you need for Clef?
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: the best quant that fits is IQ1_M (7.6 GB file, about 10.3 GB in use).
- 16 GB VRAM: the best quant that fits is Q3_K_M (13.3 GB file, about 15.9 GB in use).
- 24 GB VRAM: the best quant that fits is Q5_K_M (19.2 GB file, about 21.9 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (28.6 GB file, about 31.2 GB in use).
Which Clef quant should you choose?
Q4_K_M is the usual starting point for Clef: it balances file size and quality well. Here it is a 16.5 GB file.
The Q8_0 file is 28.6 GB, about 1.7 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.
If memory is tight, the smallest file is IQ1_M at 7.6 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
How much VRAM does Clef need?
About 19.2 GB at Q4_K_M with an 8K context window. That is the 16.5 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 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 10.3 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Clef GGUF?
It depends on the quant: IQ1_M is 7.6 GB, IQ2_M is 10.0 GB, Q2_K is 10.7 GB, IQ3_M is 12.6 GB, Q3_K_M is 13.3 GB, Q4_0 is 15.5 GB and 4 more.
What context length does Clef 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 GGUF?
The files are on Hugging Face in the abenzerps/Clef-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 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 on 8 GB VRAM?
Yes, the IQ1_M quantization is 7.63 GB and requires about 10.3 GB of VRAM at 8 k context.
Does Clef support image input?
Yes, use the included multimodal projector (clef‑mmproj‑BF16.gguf) for image or video inputs.