CL

clef flash

ClefGGUF by NANI-NithinUpdated 2026-10-04
Download on Hugging Face
Parameters8.95B
Context256K
Layers32
Architectureqwen35
Smallest quant2.0 GB
Quick answer

clef flash needs about 7.2 GB of memory at Q4_K_M (a 5.6 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 30 quants, from 2.0 GB (Q1_0) to 17.9 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Clef-Flash 9B decision model language tower

Clef-Flash is a 9B multimodal decision model based on Qwen3.5. The GGUF files provide the language tower only; the vision encoder and joint schema head are not included. The model outputs per‑question probabilities without free‑form text generation.

Good at

  • Fast inference on 8‑k context
  • Supports text, JSON, images, and video inputs
  • Returns probabilities for all question options

Limits

  • Vision encoder missing – no image/video support in GGUF
  • Joint schema head absent – cannot produce full decision outputs
  • Requires Apache‑2.0 license compliance

Best for

  • Batching multiple decision records
  • Deploying lightweight inference on GPU with limited VRAM
  • Testing language tower performance in llama.cpp

Who it’s for. Developers who need the language tower of Clef‑Flash for custom inference pipelines or benchmarking. It is suitable for those who can supply the missing vision encoder and joint head separately.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q1_02.0 GB 3.5 GB
Fits Get file →
IQ1_S2.7 GB 4.3 GB
Fits Get file →
IQ1_M2.9 GB 4.5 GB
Fits Get file →
IQ2_XXS3.1 GB 4.7 GB
Fits Get file →
IQ2_XS3.3 GB 4.9 GB
Fits Get file →
Q2_03.4 GB 4.9 GB
Fits Get file →
IQ2_S3.4 GB 5.0 GB
Fits Get file →
IQ2_M3.6 GB 5.2 GB
Fits Get file →
Q2_K_S3.7 GB 5.3 GB
Fits Get file →
Q2_K3.8 GB 5.4 GB
Fits Get file →
IQ3_XXS3.9 GB 5.5 GB
Fits Get file →
IQ3_XS4.2 GB 5.8 GB
Fits Get file →
Q3_K_S4.3 GB 5.8 GB
Fits Get file →
IQ3_S4.4 GB 5.9 GB
Fits Get file →
IQ3_M4.4 GB 6.0 GB
Fits Get file →
Q3_K_M4.6 GB 6.2 GB
Fits Get file →
Q3_K_L4.9 GB 6.5 GB
Fits Get file →
IQ4_XS5.2 GB 6.8 GB
Fits Get file →
Q4_05.3 GB 6.9 GB
Fits Get file →
Q4_K_S5.4 GB 6.9 GB
Fits Get file →
IQ4_NL5.4 GB 7.0 GB
Fits Get file →
Q4_K_M5.6 GB 7.2 GB
Tight Get file →
Q4_15.8 GB 7.4 GB
Tight Get file →
Q5_06.3 GB 7.9 GB
Tight Get file →
Q5_K_S6.3 GB 7.9 GB
Tight Get file →
Q5_K_M6.5 GB 8.0 GB
Too big Get file →
Q5_16.8 GB 8.4 GB
Too big Get file →
Q6_K7.4 GB 8.9 GB
Too big Get file →
Q8_09.5 GB 11.1 GB
Too big Get file →
BF1617.9 GB 19.5 GB
Too big Get file →

For 8‑GB VRAM, use Q4_K_M (file size 5.63 GB, memory 7.2 GB at 8 k context). If 12‑GB VRAM is available, Q5_K_M (6.47 GB, 8 GB) offers higher precision. For the lowest memory footprint, Q1_0 (1.97 GB, 3.5 GB) is suitable but with reduced quality.

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: the best quant that fits is Q1_0 (2.0 GB file, about 3.5 GB in use).
  • 6 GB VRAM: the best quant that fits is IQ3_M (4.4 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K_M (6.5 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (9.5 GB file, about 11.1 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (9.5 GB file, about 11.1 GB in use).
  • 24 GB VRAM: the best quant that fits is BF16 (17.9 GB file, about 19.5 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 5.6 GB file.

The Q8_0 file is 9.5 GB, about 1.7 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 Q1_0 at 2.0 GB, with the quality trade-offs that come with fewer bits. Lower bit counts mean smaller files and more quality loss.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35
Parameters8.95B
Layers32
Trained context262,144 tokens
KV cache (fp16)128 KB per token

Source

Quantized byNANI-Nithin
FamilyClef
Licenseapache-2.0
Downloads (HF)3,947
Last updated2026-10-04

Frequently asked questions about clef flash

How much VRAM does clef flash need?

About 7.2 GB at Q4_K_M with an 8K context window. That is the 5.6 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 6.5 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: Q1_0 is 2.0 GB, IQ1_S is 2.7 GB, IQ1_M is 2.9 GB, IQ2_XXS is 3.1 GB, IQ2_XS is 3.3 GB, Q2_0 is 3.4 GB and 24 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 NANI-Nithin/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, the Q4_K_M quant requires about 7.2 GB of VRAM at 8 k context, which fits within an 8 GB GPU.

Does the GGUF version support image inputs?

No. The GGUF files contain only the language tower; the vision encoder is not included.

What license applies to these GGUF files?

They are released under Apache‑2.0, matching the source model license.

Other GGUFs of clef-flash

Similar models

Browse all →

More from NANI-Nithin

All by NANI-Nithin →

More Clef models

All Clef →

Other small models

All small models →