CL

clef flash

ClefGGUF by LivesportUpdated 2026-10-04
Download on Hugging Face
Parameters8.95B
Context—
Layers—
Architecture—
Smallest quant0.0 GB
Quick answer

clef flash needs about 8.0 GB of memory at Q5_K_M (a 6.7 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 3 quants, from 0.0 GB to 8.6 GB (Q8_0).

Clef‑Flash: 9B decision model for multimodal inputs

Clef‑Flash is a 9B multimodal decision model based on Qwen3.5‑9B. It reads text, JSON, images, or video and outputs probabilities for each question option in a single forward pass. The model does not generate free‑form text.

Good at

  • Decision making from multimodal state
  • Fast inference on 8 GB GPUs
  • Jev/SystemOne API compatibility

Limits

  • No text generation
  • Requires llama.cpp 8212c78
  • No vision support on older GPUs

Best for

  • Real‑time decision engines
  • Batch inference of structured queries
  • Production inference on single 8 GB GPU

Who it’s for. Engineers building decision‑making services that need fast, deterministic outputs from multimodal inputs. Suitable for production environments where text generation is not required.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 0.5 GB
Fits Get file →
Q5_K_M6.7 GB 8.0 GB
Tight Get file →
Q8_08.6 GB 10.1 GB
Too big Get file →

For 8 GB VRAM use the Q5_K_M GGUF (6.66 GB file, ~8 GB memory). The Q8_0 GGUF (8.58 GB file, ~10.1 GB memory) exceeds 8 GB VRAM. The unknown‑quant file is tiny but not recommended for production.

What GPU do you need for clef flash?

These figures add the file size, an fp16 KV cache at an 8K context window 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: the best quant that fits is the main file (0.0 GB file, about 0.5 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 0.5 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K_M (6.7 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (8.6 GB file, about 10.1 GB in use).

Which clef flash quant should you choose?

Q5_K_M (6.7 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Parameters8.95B

Source

Quantized byLivesport
FamilyClef
Licenseapache-2.0
Downloads (HF)1,880
Last updated2026-10-04

Frequently asked questions about clef flash

How much VRAM does clef flash need?

About 8.0 GB at Q5_K_M with an 8K context window. That is the 6.7 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 flash on an 8 GB GPU?

Yes, with Q5_K_M: the 6.7 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of clef flash GGUF?

It depends on the quant: file is 0.0 GB, Q5_K_M is 6.7 GB, Q8_0 is 8.6 GB.

Where can I download clef flash GGUF?

The files are on Hugging Face in the Livesport/clef-flash-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 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.

Does Clef‑Flash generate text?

No. The model outputs probabilities for each question option and does not produce free‑form text.

What inputs does Clef‑Flash support?

It accepts text, JSON, images, and video as part of the state and schema.

Other GGUFs of clef-flash

Similar models

Browse all →

More from Livesport

All by Livesport →

More Clef models

All Clef →

Other small models

All small models →