clef flash mixed vision needs about 4.9 GB of memory at its main file (a 3.3 GB file) with an 8K context window, so it fits on a 6 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
Clef Flash mixed vision 8.95B multimodal decision model
Clef Flash mixed vision is an 8.95B Qwen3.5‑based model that accepts text, JSON, images, or video and outputs decision probabilities. It has no free‑form text generation and uses a joint schema head for scoring options. The GGUF file is 3.3 GB with 4.9 GB estimated memory at 8 k context.
Good at
- Multimodal decision making
- Image and video input
- Probability scoring per question
Limits
- No free‑form text generation
- No official Cloudflare release
- Requires separate mmproj for vision
Best for
- Decision‑making pipelines
- Vision‑enabled QA systems
- Batch inference of structured queries
Who it’s for. Developers building decision‑oriented AI that needs image or video context. The model is useful for applications that require probability outputs for multiple choice, true/false, or score questions without generating text.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 3.3 GB | 4.9 GB | Fits | Get file → |
The available GGUF file is 3.3 GB with an estimated 4.9 GB memory requirement at 8 k context. This is the only quant available, so use it if your GPU has at least 8 GB VRAM. No other quant formats are listed.
What GPU do you need for clef flash mixed vision?
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: the best quant that fits is the main file (3.3 GB file, about 4.9 GB in use).
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about clef flash mixed vision
How much VRAM does clef flash mixed vision need?
About 4.9 GB at its main file with an 8K context window. That is the 3.3 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 clef flash mixed vision on an 8 GB GPU?
Yes, with the smaller files: the 3.3 GB file needs about 4.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of clef flash mixed vision GGUF?
It depends on the quant: file is 3.3 GB.
What context length does clef flash mixed vision support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.
Where can I download clef flash mixed vision GGUF?
The files are on Hugging Face in the Jakevin/clef-flash-mixed-vision-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 flash mixed vision 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 this model on 8 GB VRAM?
The model requires about 4.9 GB of memory at 8 k context, so 8 GB VRAM should be sufficient for inference.
Does this model support text generation?
No, it does not produce free‑form text; it only outputs decision probabilities.
Is this an official Cloudflare release?
No, it is an unofficial post‑training quantization and is not endorsed by Cloudflare.