CL

Clef Flash Heretic

ClefGGUF by mradermacherUpdated 2026-10-06
Download on Hugging Face
Parameters8.95B
Context256K
Layers32
Architectureqwen35
Smallest quant0.0 GB
Quick answer

Clef Flash Heretic 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 25 quants, from 0.0 GB to 7.4 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

9B multimodal decision model on Qwen3.5 backbone

Clef Flash Heretic is a 9B vision model that reads state and a schema of typed questions and returns a probability for each allowed option in a single forward pass. It is a decensored variant of Clef-Flash with targeted weight edits to suppress refusals. The model runs locally via GGUF on a 16 GB GPU.

Good at

  • Decision‑making with typed outputs
  • Low refusal rate after abliteration
  • Multimodal vision support

Limits

  • No free‑text generation
  • Requires 16 GB VRAM for full 9B model
  • License is Apache‑2.0

Best for

  • Moderation triage pipelines
  • Risk scoring systems
  • Content classification workflows

Who it’s for. Engineers building classification and decision pipelines who need a narrow, low‑refusal model. The model is suitable for local deployment on gaming PCs with 16 GB VRAM.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 1.6 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 →
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_K_S6.3 GB 7.9 GB
Tight Get file →
Q5_K_M6.5 GB 8.0 GB
Too big Get file →
Q6_K7.4 GB 8.9 GB
Too big Get file →

For 8 GB VRAM, use Q4_0 (5.33 GB, ~6.9 GB memory at 8 k context). For 12 GB VRAM, Q4_K_M (5.63 GB, ~7.2 GB memory). For 16 GB VRAM, the full 9B model (unknown quant) or Q6_K (7.36 GB, ~8.9 GB memory) is recommended. Memory estimates are approximate.

What GPU do you need for Clef Flash Heretic?

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 the main file (0.0 GB file, about 1.6 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 Q6_K (7.4 GB file, about 8.9 GB in use).

Which Clef Flash Heretic quant should you choose?

Q4_K_M is the usual starting point for Clef Flash Heretic: it balances file size and quality well. Here it is a 5.6 GB file.

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

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

Source

Quantized bymradermacher
FamilyClef
Licenseapache-2.0
Downloads (HF)5,951
Last updated2026-10-06

Frequently asked questions about Clef Flash Heretic

How much VRAM does Clef Flash Heretic 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 Heretic 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 Heretic GGUF?

It depends on the quant: file is 0.0 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, IQ2_S is 3.4 GB and 19 more.

What context length does Clef Flash Heretic 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 Heretic GGUF?

The files are on Hugging Face in the mradermacher/clef-flash-heretic-i1-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 Heretic 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 Heretic on 8 GB VRAM?

Use the Q4_0 quant, which is 5.33 GB and requires about 6.9 GB VRAM at 8 k context.

Does this model support text generation?

No, it outputs only typed probabilities and does not generate free text.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of clef-flash-heretic

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Clef models

All Clef →

Other small models

All small models →