AP

Apertus 70B Instruct 2509 Heretic v2

ApertusGGUF by mradermacherUpdated 2026-04-11
Download on Hugging Face
Parameters70.6B
Context64K
Layers80
Architectureapertus
Smallest quant0.0 GB
Quick answer

Apertus 70B Instruct 2509 Heretic v2 needs about 46.9 GB of memory at Q4_K_M (a 43.7 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 24 quants, from 0.0 GB to 57.9 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.

Apertus 70B Instruct 2509 Heretic v2 – 70.6B parameter open multilingual LLM

Apertus 70B Instruct 2509 Heretic v2 is a 70.6B parameter decoder‑only transformer with 65,536 token context. It supports over 1000 languages and tool use. The model is fully open with Apache‑2.0 license.

Good at

  • Long‑context reasoning
  • Tool usage
  • Multilingual support

Limits

  • No vision support
  • Requires large VRAM for full precision
  • License is Apache‑2.0

Best for

  • Complex reasoning tasks
  • Agentic workflows with tools
  • Large‑scale multilingual content generation

Who it’s for. Developers building agentic applications or researchers needing a large, open, multilingual model. The model is suitable for environments with sufficient GPU memory and a need for transparent training data.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 3.2 GB
Fits Get file →
IQ1_S15.5 GB 18.7 GB
Too big Get file →
IQ1_M16.9 GB 20.1 GB
Too big Get file →
IQ2_XXS19.2 GB 22.4 GB
Too big Get file →
IQ2_XS21.2 GB 24.4 GB
Too big Get file →
IQ2_S22.4 GB 25.6 GB
Too big Get file →
IQ2_M24.3 GB 27.5 GB
Too big Get file →
Q2_K_S24.7 GB 27.9 GB
Too big Get file →
Q2_K27.3 GB 30.5 GB
Too big Get file →
IQ3_XXS27.4 GB 30.6 GB
Too big Get file →
IQ3_XS29.6 GB 32.8 GB
Too big Get file →
Q3_K_S30.8 GB 34.0 GB
Too big Get file →
IQ3_S30.9 GB 34.0 GB
Too big Get file →
IQ3_M32.0 GB 35.2 GB
Too big Get file →
Q3_K_M35.5 GB 38.7 GB
Too big Get file →
IQ4_XS37.9 GB 41.1 GB
Too big Get file →
Q3_K_L39.6 GB 42.8 GB
Too big Get file →
Q4_040.2 GB 43.4 GB
Too big Get file →
Q4_K_S40.4 GB 43.6 GB
Too big Get file →
Q4_K_M43.7 GB 46.9 GB
Too big Get file →
Q4_144.3 GB 47.5 GB
Too big Get file →
Q5_K_S48.7 GB 51.9 GB
Too big Get file →
Q5_K_M50.6 GB 53.8 GB
Too big Get file →
Q6_K57.9 GB 61.1 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (file size 43.72 GB, estimated memory 46.9 GB at 8 k context). For 12 GB VRAM, Q3_K_M (35.54 GB, 38.7 GB). For 16 GB VRAM, Q2_K (27.27 GB, 30.5 GB). Estimates are approximate.

What GPU do you need for Apertus 70B Instruct 2509 Heretic v2?

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 3.2 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 3.2 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 3.2 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 3.2 GB in use).
  • 16 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 3.2 GB in use).
  • 24 GB VRAM: the best quant that fits is IQ2_XXS (19.2 GB file, about 22.4 GB in use).
  • 32 GB VRAM: the best quant that fits is IQ3_XXS (27.4 GB file, about 30.6 GB in use).
  • 48 GB VRAM: the best quant that fits is Q4_1 (44.3 GB file, about 47.5 GB in use).

Which Apertus 70B Instruct 2509 Heretic v2 quant should you choose?

Q4_K_M is the usual starting point for Apertus 70B Instruct 2509 Heretic v2: it balances file size and quality well. Here it is a 43.7 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
Parameters70.6B
Layers80
Trained context65,536 tokens
KV cache (fp16)320 KB per token

Source

Quantized bymradermacher
FamilyApertus
Licenseapache-2.0
Downloads (HF)567
Last updated2026-04-11

Frequently asked questions about Apertus 70B Instruct 2509 Heretic v2

How much VRAM does Apertus 70B Instruct 2509 Heretic v2 need?

About 46.9 GB at Q4_K_M with an 8K context window. That is the 43.7 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 Apertus 70B Instruct 2509 Heretic v2 on an 8 GB GPU?

Yes, with the smaller files: the 0.0 GB file needs about 3.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Apertus 70B Instruct 2509 Heretic v2 GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 15.5 GB, IQ1_M is 16.9 GB, IQ2_XXS is 19.2 GB, IQ2_XS is 21.2 GB, IQ2_S is 22.4 GB and 18 more.

What context length does Apertus 70B Instruct 2509 Heretic v2 support?

The GGUF header lists a trained context length of 65,536 tokens (64K). The KV cache grows with the context you use: about 2.7 GB at 8K and 10.7 GB at 32K.

Where can I download Apertus 70B Instruct 2509 Heretic v2 GGUF?

The files are on Hugging Face in the mradermacher/Apertus-70B-Instruct-2509-heretic-v2-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 70B Instruct 2509 Heretic v2 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 this model on 8 GB VRAM?

The Q4_K_M quant uses about 46.9 GB of VRAM at 8 k context, so 8 GB VRAM is insufficient.

Does the model support vision?

No, the model has no vision capabilities.

What license does the model use?

The model is released under the Apache‑2.0 license.

Other GGUFs of Apertus-70B-Instruct-2509-heretic-v1.1.2

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Apertus models

All Apertus →

Other large models

All large models →