CL

Clef Flash Heretic

ClefGGUF by mradermacherUpdated 2026-10-06
Download on Hugging Face
Parameters8.95B
Context256K
Layers32
Architectureqwen35
Smallest quant3.8 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 12 quants, from 3.8 GB (Q2_K) to 17.9 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Clef Flash Heretic – a 9B multimodal decision model on a Qwen3.5 backbone

Clef Flash Heretic is a 9B multimodal decision model that reads state and a schema of typed questions and returns a probability for every allowed option in a single forward pass. It removes refusal behaviour via targeted weight edits, keeping the Decision Index scoring and typed‑output head intact.

Good at

  • Decision‑making with typed outputs
  • Low refusal rates on harmful prompts
  • Multimodal vision support

Limits

  • Requires 16 GB GPU for full 9B model
  • No free‑text generation
  • Limited to decision‑type prompts

Best for

  • Moderation triage pipelines
  • Routing and risk scoring
  • Content classification systems

Who it’s for. Engineers building classification and decision pipelines who need low‑refusal models for moderation triage, routing, and risk scoring. The model outputs only typed probabilities, making it suitable for narrow decision tasks.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K3.8 GB 5.4 GB
Fits Get file →
Q3_K_S4.3 GB 5.8 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_K_S5.4 GB 6.9 GB
Fits Get file →
Q4_K_M5.6 GB 7.2 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 →
Q8_09.5 GB 11.1 GB
Too big Get file →
F1617.9 GB 19.5 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (5.63 GB file, ~7.2 GB memory at 8k context). For 12 GB VRAM, Q5_K_M (6.47 GB file, ~8 GB memory). For 16 GB VRAM, the full F16 (17.92 GB file, ~19.5 GB memory) gives the highest quality.

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: no quant fits at an 8K context.
  • 6 GB VRAM: the best quant that fits is Q3_K_S (4.3 GB file, about 5.8 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 F16 (17.9 GB file, about 19.5 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.

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 Q2_K at 3.8 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

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

Source

Quantized bymradermacher
FamilyClef
Licenseapache-2.0
Downloads (HF)20,121
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: Q2_K is 3.8 GB, Q3_K_S is 4.3 GB, Q3_K_M is 4.6 GB, Q3_K_L is 4.9 GB, IQ4_XS is 5.2 GB, Q4_K_S is 5.4 GB and 6 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-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_K_M quant, which requires about 7.2 GB of VRAM at 8k context.

Does this model support text generation?

No, it only outputs typed probabilities for decision tasks.

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 →