AP

Apertus 70B Instruct 2509 Abliterated

ApertusGGUF by mradermacherUpdated 2025-10-04
Download on Hugging Face
Parameters70.6B
Context64K
Layers80
Architectureapertus
Smallest quant27.3 GB
Quick answer

Apertus 70B Instruct 2509 Abliterated 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 8 quants, from 27.3 GB (Q2_K) to 48.7 GB (Q5_K_S). Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.

Apertus 70B Instruct 2509 Abliterated – a 70.6B parameter instruction model

Apertus 70B Instruct 2509 Abliterated is a 70.6B parameter model built on the apertus architecture. It supports reasoning and tool usage and was trained on a context of 65536 tokens. The model is available in multiple GGUF quantizations.

Good at

  • Reasoning tasks
  • Tool integration
  • Long‑context handling

Limits

  • No vision support
  • License not specified
  • Large VRAM requirement

Best for

  • Complex reasoning workflows
  • Tool‑enabled automation
  • Long‑form content generation

Who it’s for. Developers and researchers needing a large instruction‑tuned model for reasoning and tool use. Suitable for applications that can accommodate the model’s memory demands.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K27.3 GB 30.5 GB
Too big Get file →
Q3_K_S30.8 GB 34.0 GB
Too big Get file →
Q3_K_M35.5 GB 38.7 GB
Too big Get file →
IQ4_XS38.5 GB 41.7 GB
Too big Get file →
Q3_K_L39.6 GB 42.8 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 →
Q5_K_S48.7 GB 51.9 GB
Too big Get file →

For 8‑GB VRAM, use Q2_K (27.27 GB file, ~30.5 GB memory). For 12‑GB VRAM, Q3_K_S (30.77 GB file, ~34 GB memory) is suitable. For 16‑GB VRAM, Q3_K_M (35.54 GB file, ~38.7 GB memory) offers a balance of size and performance.

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

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: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: no quant fits at an 8K context.
  • 32 GB VRAM: the best quant that fits is Q2_K (27.3 GB file, about 30.5 GB in use).
  • 48 GB VRAM: the best quant that fits is Q4_K_M (43.7 GB file, about 46.9 GB in use).

Which Apertus 70B Instruct 2509 Abliterated quant should you choose?

Q4_K_M is the usual starting point for Apertus 70B Instruct 2509 Abliterated: it balances file size and quality well. Here it is a 43.7 GB file.

If memory is tight, the smallest file is Q2_K at 27.3 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

Architectureapertus
Parameters70.6B
Layers80
Trained context65,536 tokens
KV cache (fp16)320 KB per token

Source

Quantized bymradermacher
FamilyApertus
Downloads (HF)199
Last updated2025-10-04

Frequently asked questions about Apertus 70B Instruct 2509 Abliterated

How much VRAM does Apertus 70B Instruct 2509 Abliterated 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 Abliterated on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 30.5 GB, so you would need a larger GPU or CPU offloading.

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

It depends on the quant: Q2_K is 27.3 GB, Q3_K_S is 30.8 GB, Q3_K_M is 35.5 GB, IQ4_XS is 38.5 GB, Q3_K_L is 39.6 GB, Q4_K_S is 40.4 GB and 2 more.

What context length does Apertus 70B Instruct 2509 Abliterated 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 Abliterated GGUF?

The files are on Hugging Face in the mradermacher/Apertus-70B-Instruct-2509-abliterated-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run this model on 8 GB VRAM?

Yes, the Q2_K quant requires about 30.5 GB memory at 8k context, which is beyond 8 GB VRAM, so it cannot run on 8 GB VRAM.

Does the model support vision?

No, the model does not include vision capabilities.

What is the maximum context length?

The model was trained with a context of 65536 tokens.

Other GGUFs of Apertus-70B-Instruct-2509-abliterated

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Apertus models

All Apertus →

Other large models

All large models →