CL

Clef Flash

ClefGGUF by bartowskiUpdated 2026-10-05
Download on Hugging Face
Parameters9.1B
Context256K
Layers32
Architectureclef
Smallest quant4.2 GB
Quick answer

Clef Flash needs about 7.6 GB of memory at Q4_K_M (a 6.0 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 18 quants, from 4.2 GB (Q2_K) to 18.2 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Clef Flash – a 9B multimodal decision model for text, image, and video inputs

Clef Flash is a 9.1‑billion parameter multimodal model that outputs probabilities for a set of predefined questions. It accepts text, JSON, images, or video as state and returns a probability for each allowed option in a single forward pass. No free‑form text generation is performed.

Good at

  • Decision making from multimodal input
  • Fast inference with static quantization
  • Supports text, image, and video states

Limits

  • No free‑form text generation
  • Requires llama.cpp static quantization
  • No imatrix calibration available

Best for

  • Automated decision systems
  • Batch evaluation of structured queries
  • Integration with Jev/SystemOne APIs

Who it’s for. Developers building decision‑oriented applications that need rapid, multimodal inference without text generation. The model is suitable for systems that process structured queries over text, images, or video and return probability distributions.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K4.2 GB 5.8 GB
Fits Get file →
Q3_K_S4.8 GB 6.4 GB
Fits Get file →
IQ3_M4.9 GB 6.4 GB
Fits Get file →
Q3_K_M5.0 GB 6.6 GB
Fits Get file →
Q3_K_L5.2 GB 6.8 GB
Fits Get file →
IQ4_XS5.4 GB 7.0 GB
Fits Get file →
Q4_05.6 GB 7.2 GB
Fits Get file →
IQ4_NL5.6 GB 7.2 GB
Tight Get file →
Q4_K_S5.7 GB 7.3 GB
Tight Get file →
Q4_K_M6.0 GB 7.6 GB
Tight Get file →
Q4_16.1 GB 7.6 GB
Tight Get file →
Q5_K_S6.7 GB 8.2 GB
Too big Get file →
Q4_K_L6.8 GB 8.4 GB
Too big Get file →
Q5_K_M7.0 GB 8.6 GB
Too big Get file →
Q6_K7.8 GB 9.4 GB
Too big Get file →
Q6_K_L8.3 GB 9.9 GB
Too big Get file →
Q8_09.7 GB 11.2 GB
Too big Get file →
BF1618.2 GB 19.7 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (6.04 GB file, ~7.6 GB VRAM at 8 k context). For 12 GB VRAM, Q5_K_S (6.66 GB file, ~8.2 GB VRAM) offers higher quality. Larger VRAM allows Q6_K or Q8_0 for best performance.

What GPU do you need for Clef Flash?

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 Q2_K (4.2 GB file, about 5.8 GB in use).
  • 8 GB VRAM: the best quant that fits is Q4_1 (6.1 GB file, about 7.6 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (9.7 GB file, about 11.2 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (9.7 GB file, about 11.2 GB in use).
  • 24 GB VRAM: the best quant that fits is BF16 (18.2 GB file, about 19.7 GB in use).

Which Clef Flash quant should you choose?

Q4_K_M is the usual starting point for Clef Flash: it balances file size and quality well. Here it is a 6.0 GB file.

The Q8_0 file is 9.7 GB, about 1.6 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 Q2_K at 4.2 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

Architectureclef
Parameters9.1B
Layers32
Trained context262,144 tokens
KV cache (fp16)128 KB per token

Source

Quantized bybartowski
FamilyClef
Licenseapache-2.0
Downloads (HF)42,872
Last updated2026-10-05

Frequently asked questions about Clef Flash

How much VRAM does Clef Flash need?

About 7.6 GB at Q4_K_M with an 8K context window. That is the 6.0 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 Q4_1: the 6.1 GB file needs about 7.6 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: Q2_K is 4.2 GB, Q3_K_S is 4.8 GB, IQ3_M is 4.9 GB, Q3_K_M is 5.0 GB, Q3_K_L is 5.2 GB, IQ4_XS is 5.4 GB and 12 more.

What context length does Clef Flash 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 GGUF?

The files are on Hugging Face in the bartowski/Cloudflare_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.

Can I run Clef Flash on 8 GB VRAM?

Yes, using the Q4_K_M quantization which requires about 7.6 GB VRAM at 8 k context.

Does Clef Flash support text generation?

No, it is a decision model and only returns probabilities for predefined options.

What quantization is recommended for best quality?

Use Q4_K_M or larger; lower‑bit quantizations like Q3_K_L or Q2_K lose noticeable quality.

Other GGUFs of clef-flash

Similar models

Browse all →

More from bartowski

All by bartowski →

More Clef models

All Clef →

Other small models

All small models →