AP

Apertus 8B Instruct 2509 Heretic

ApertusGGUF by mradermacherUpdated 2026-01-06
Download on Hugging Face
Parameters8.05B
Context64K
Layers32
Architectureapertus
Smallest quant0.0 GB
Quick answer

Apertus 8B Instruct 2509 Heretic needs about 6.6 GB of memory at Q4_K_M (a 5.1 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 6.6 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Apertus 8B Instruct 2509 Heretic – 8.05B parameter multilingual decoder

Apertus 8B Instruct 2509 Heretic is a 8.05B parameter decoder‑only transformer. It supports a context length of 65,536 tokens and is trained on 15T tokens of web, code and math data. The model is fully open under the Apache‑2.0 license.

Good at

  • Multilingual reasoning
  • Tool use
  • Long‑context processing

Limits

  • No vision support
  • Requires 65,536 token context
  • License is Apache‑2.0

Best for

  • Chatbots needing long context
  • Multilingual content generation
  • Tool‑enabled agents

Who it’s for. Developers building open‑source LLM applications that need a large, multilingual model with tool‑use capability. The model is suitable for research and production use where open weights and data are required.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 1.6 GB
Fits Get file →
IQ1_S2.0 GB 3.6 GB
Fits Get file →
IQ1_M2.2 GB 3.8 GB
Fits Get file →
IQ2_XXS2.4 GB 4.0 GB
Fits Get file →
IQ2_XS2.6 GB 4.2 GB
Fits Get file →
IQ2_S2.8 GB 4.4 GB
Fits Get file →
IQ2_M3.0 GB 4.5 GB
Fits Get file →
Q2_K_S3.0 GB 4.6 GB
Fits Get file →
IQ3_XXS3.3 GB 4.9 GB
Fits Get file →
Q2_K3.3 GB 4.9 GB
Fits Get file →
IQ3_XS3.6 GB 5.1 GB
Fits Get file →
Q3_K_S3.7 GB 5.3 GB
Fits Get file →
IQ3_S3.7 GB 5.3 GB
Fits Get file →
IQ3_M3.8 GB 5.4 GB
Fits Get file →
Q3_K_M4.2 GB 5.7 GB
Fits Get file →
IQ4_XS4.5 GB 6.0 GB
Fits Get file →
Q3_K_L4.6 GB 6.2 GB
Fits Get file →
IQ4_NL4.7 GB 6.3 GB
Fits Get file →
Q4_04.7 GB 6.3 GB
Fits Get file →
Q4_K_S4.7 GB 6.3 GB
Fits Get file →
Q4_K_M5.1 GB 6.6 GB
Fits Get file →
Q4_15.1 GB 6.7 GB
Fits Get file →
Q5_K_S5.6 GB 7.2 GB
Fits Get file →
Q5_K_M5.8 GB 7.4 GB
Tight Get file →
Q6_K6.6 GB 8.2 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (2.05 GB, 3.6 GB memory at 8 k context) or IQ1_M (2.19 GB, 3.8 GB). For 12 GB VRAM, IQ2_S (2.62 GB, 4.2 GB) or Q2_K_S (3.03 GB, 4.6 GB) are good choices. For 16 GB VRAM, Q4_K_M (5.06 GB, 6.6 GB) or Q5_K_S (5.62 GB, 7.2 GB) provide higher quality while staying within budget. The estimates are approximate.

What GPU do you need for Apertus 8B Instruct 2509 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 IQ2_XXS (2.4 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is IQ4_XS (4.5 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K_M (5.8 GB file, about 7.4 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (6.6 GB file, about 8.2 GB in use).

Which Apertus 8B Instruct 2509 Heretic quant should you choose?

Q4_K_M is the usual starting point for Apertus 8B Instruct 2509 Heretic: it balances file size and quality well. Here it is a 5.1 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

Architectureapertus
Parameters8.05B
Layers32
Trained context65,536 tokens
KV cache (fp16)128 KB per token

Source

Quantized bymradermacher
FamilyApertus
Licenseapache-2.0
Downloads (HF)1,093
Last updated2026-01-06

Frequently asked questions about Apertus 8B Instruct 2509 Heretic

How much VRAM does Apertus 8B Instruct 2509 Heretic need?

About 6.6 GB at Q4_K_M with an 8K context window. That is the 5.1 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 Apertus 8B Instruct 2509 Heretic on an 8 GB GPU?

Yes, with Q5_K_M: the 5.8 GB file needs about 7.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Apertus 8B Instruct 2509 Heretic GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 2.0 GB, IQ1_M is 2.2 GB, IQ2_XXS is 2.4 GB, IQ2_XS is 2.6 GB, IQ2_S is 2.8 GB and 19 more.

What context length does Apertus 8B Instruct 2509 Heretic support?

The GGUF header lists a trained context length of 65,536 tokens (64K). 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 Apertus 8B Instruct 2509 Heretic GGUF?

The files are on Hugging Face in the mradermacher/Apertus-8B-Instruct-2509-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 Apertus 8B Instruct 2509 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 Apertus 8B Instruct 2509 Heretic on 8 GB VRAM?

Yes, using the IQ1_S or IQ1_M quantized files will fit within 8 GB VRAM, with estimated memory usage of 3.6–3.8 GB at 8 k context.

Does the model support vision or image input?

No, the model does not include vision capabilities and is purely text‑based.

What license applies to this model?

The model is released under the Apache‑2.0 license, allowing free use and modification.

Other GGUFs of Apertus-8B-Instruct-2509-Heretic

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Apertus models

All Apertus →

Other small models

All small models →