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 3 quants, from 16.5 GB (Q4_K_M) to 53.8 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.
27B multimodal decision model for structured outputs
Clef is a 26.9B parameter model that reads text, JSON, images, or video and returns probabilities for each question in a single pass. It uses a joint schema head on a Qwen3.8 backbone and produces logits per option, eliminating output parsing.
Good at
- Structured decision making
- Multimodal input handling
- Batch scoring of multiple questions
Limits
- No free‑form text generation
- No output parsing
- Default input limit 16,384 tokens
Best for
- Decision‑making APIs
- Mixed text and image workflows
- Batch evaluation of schema questions
Who it’s for. Developers building decision systems that need fast, structured predictions from multimodal data. The model is compatible with the Jev/SystemOne API and supports mixed batches.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| 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 → | |
| BF16 | 53.8 GB | 56.5 GB | Too big | Get file → |
For 8–12 GB VRAM, use Q4_K_M (file size 16.55 GB, estimated 19.2 GB memory at 8 k context). For 12–20 GB VRAM, Q5_K_M (19.23 GB, 21.9 GB memory) is suitable. For larger GPUs, BF16 (53.81 GB, 56.5 GB memory) offers higher precision.
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: 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 Q5_K_M (19.2 GB file, about 21.9 GB in use).
- 32 GB VRAM: the best quant that fits is Q5_K_M (19.2 GB file, about 21.9 GB in use).
- 48 GB VRAM: the best quant that fits is Q5_K_M (19.2 GB file, about 21.9 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.
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 19.2 GB, so you would need a larger GPU or CPU offloading.
What is the file size of clef GGUF?
It depends on the quant: Q4_K_M is 16.5 GB, Q5_K_M is 19.2 GB, BF16 is 53.8 GB.
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 prithivMLmods/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?
Use the Q4_K_M quantized file; it requires about 19.2 GB memory at 8 k context, so 8 GB VRAM is insufficient.
Does Clef generate free‑form text?
No, it outputs only logits per option and probabilities, with no text generation.
What is the default token limit for inputs?
The model limits inputs to 16,384 tokens by default.