CL

Cloudflare clef

ClefGGUF by bartowskiUpdated 2026-10-06
Download on Hugging Face
Parameters27B
Context256K
Layers64
Architectureclef
Smallest quant11.7 GB
Quick answer

Cloudflare clef needs about 20.3 GB of memory at Q4_K_M (a 17.7 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 18 quants, from 11.7 GB (Q2_K) to 54.1 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.

27B multimodal decision model for structured queries

Cloudflare clef is a 27B multimodal model that reads text, JSON, images, or video and returns probabilities for each option in a set of typed questions. It performs a single forward pass and never generates free‑form text. The model is licensed under Apache‑2.0.

Good at

  • Decision making from multimodal input
  • Fast single‑pass inference
  • No text generation needed

Limits

  • No free‑form text output
  • Requires image/video support via pillow
  • Large VRAM needed for higher quants

Best for

  • Automated decision systems
  • Structured QA pipelines
  • Batch inference of multiple schemas

Who it’s for. Developers building systems that need to evaluate structured questions from text or images. It is suitable for backend services that require deterministic probability outputs without text generation.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K11.7 GB 14.4 GB
Too big Get file →
Q3_K_S13.6 GB 16.2 GB
Too big Get file →
IQ3_M13.8 GB 16.4 GB
Too big Get file →
Q3_K_M14.5 GB 17.1 GB
Too big Get file →
Q3_K_L15.2 GB 17.8 GB
Too big Get file →
IQ4_XS15.6 GB 18.2 GB
Too big Get file →
Q4_016.2 GB 18.8 GB
Too big Get file →
IQ4_NL16.3 GB 18.9 GB
Too big Get file →
Q4_K_S16.6 GB 19.2 GB
Too big Get file →
Q4_K_M17.7 GB 20.3 GB
Too big Get file →
Q4_117.7 GB 20.4 GB
Too big Get file →
Q4_K_L18.6 GB 21.2 GB
Too big Get file →
Q5_K_S19.6 GB 22.2 GB
Too big Get file →
Q5_K_M20.6 GB 23.3 GB
Too big Get file →
Q6_K23.3 GB 26.0 GB
Too big Get file →
Q6_K_L24.0 GB 26.6 GB
Too big Get file →
Q8_028.8 GB 31.4 GB
Too big Get file →
BF1654.1 GB (2 parts) 56.7 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (17.65 GB file, ~20.3 GB VRAM). For 12 GB VRAM, Q4_K_L (18.6 GB file, ~21.2 GB VRAM). For 16 GB VRAM, Q5_K_S (19.57 GB file, ~22.2 GB VRAM). These quants balance size and quality.

What GPU do you need for Cloudflare 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: the best quant that fits is Q2_K (11.7 GB file, about 14.4 GB in use).
  • 24 GB VRAM: the best quant that fits is Q5_K_M (20.6 GB file, about 23.3 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (28.8 GB file, about 31.4 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (28.8 GB file, about 31.4 GB in use).

Which Cloudflare clef quant should you choose?

Q4_K_M is the usual starting point for Cloudflare clef: it balances file size and quality well. Here it is a 17.7 GB file.

The Q8_0 file is 28.8 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 11.7 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
Parameters27B
Layers64
Trained context262,144 tokens
KV cache (fp16)256 KB per token

Source

Quantized bybartowski
FamilyClef
Base modelCloudflare/clef
Licenseapache-2.0
Downloads (HF)42,490
Last updated2026-10-06

Frequently asked questions about Cloudflare clef

How much VRAM does Cloudflare clef need?

About 20.3 GB at Q4_K_M with an 8K context window. That is the 17.7 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 Cloudflare clef on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 14.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Cloudflare clef GGUF?

It depends on the quant: Q2_K is 11.7 GB, Q3_K_S is 13.6 GB, IQ3_M is 13.8 GB, Q3_K_M is 14.5 GB, Q3_K_L is 15.2 GB, IQ4_XS is 15.6 GB and 12 more.

What context length does Cloudflare 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 Cloudflare clef GGUF?

The files are on Hugging Face in the bartowski/Cloudflare_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 Cloudflare 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 Cloudflare clef on 8 GB VRAM?

Use the Q4_K_M quant; it requires about 20.3 GB VRAM, so 8 GB is insufficient.

Does clef support image input?

Yes, clef accepts images via pillow and can process multimodal records.

Is there a text‑generation endpoint?

No, clef is a decision model and does not generate free‑form text.

Other GGUFs of clef

Similar models

Browse all →

More from bartowski

All by bartowski →

More Clef models

All Clef →

Other medium models

All medium models →