OpenModelsHQ

Apertus-70B-Instruct-2509

Swiss AI InitiativeLLMDenseApache-2.0

Apertus-70B-Instruct-2509 is an open-weight language model from Swiss AI Initiative with 70.6B parameters. At 4-bit it needs about 49.5 GB of memory, so the smallest current device that fits it is the A100 80GB SXM.

Overview

Estimated memory at 4-bit
49.5GB

Includes room for an 8k context and runtime overhead. More context needs more memory.

Total parameters
70.6B
Dense
Context window
64K
65,536 tokens
Cheapest API, blended / 1M
No hosted API
Weights only

Key information

Lab
Swiss AI Initiative
Released
1 Sep 2025
Parameters
70.6B
Type
Language
Context
65,536 tokens
License
Apache-2.0
HF downloads, 30 days
8,423
View all

Will it run on your hardware?

How we estimate
Memory needed vs devices
Apertus-70B-Instruct-2509 needs about 49.5 GB at 4-bit, 85.3 GB at 8-bit and 158.3 GB at 16-bit. At 4-bit it fits DGX Spark, Mac Studio M5 Ultra (256GB). Dashed lines are usable memory on each device; a model fits when its estimate stays within 90% of it. Log scale. 8k context.
Memory needed vs devices: data
Estimate or deviceMemory
Q449.5 GB
Q885.3 GB
BF16158.3 GB
RTX 5060 Ti 16 GB16 GB usable
RTX 5090 32 GB32 GB usable
DGX Spark 128 GB108.8 GB usable
Mac Studio M5 Ultra 256 GB192 GB usable

Single-device memory estimate. Pick a device to update the On your device column.

36 GB usable memory

FormatMemory neededOn your deviceExample hardware
4-bit (Q4)≈ 49.5 GBToo big 138%A100 80GB SXM80 GB memory
8-bit (Q8)≈ 85.3 GBToo big 237%RTX PRO 6000 Blackwell96 GB memory
16-bit (BF16)≈ 158.3 GBToo big 440%Mac Studio M5 Ultra (256GB)256 GB memory

Fits means the estimate stays within 90% of usable memory. Tight is above 90% and up to 100%. Too big is above 100%. These are memory checks, not speed or compatibility tests.

Mac allowances are 66% of total RAM up to 36 GB, and 75% above. AI boxes allow 85% because their memory is shared with the operating system.

Where to run it

On a Mac

No trusted MLX build found yet.

Check your Mac

With GGUF

Choose a file for llama.cpp or a compatible app.

unsloth/Apertus-70B-Instruct-2509-GGUFFind compatible hardware

Through an API

No hosted API found.

GGUF with llama.cppView repository
llama-cli -hf unsloth/Apertus-70B-Instruct-2509-GGUF \
  -c 8192 -p "Explain how a transformer works."

Example commands built from the repository ids above. They need a working install of llama.cpp. We have not run them; check each repository for available files.

More about this model

Frequently asked questions

How much memory does Apertus-70B-Instruct-2509 need? At an 8k context, about 49.5 GB at 4-bit, 85.3 GB at 8-bit and 158.3 GB at 16-bit (BF16). A longer context needs more.

Can I run Apertus-70B-Instruct-2509 on a Mac? The smallest current Mac that fits the 4-bit estimate of 49.5 GB is the Mac Studio M5 Ultra (96GB). We have not found a trusted MLX build yet, but a GGUF build is available.

Does the full context fit? Apertus-70B-Instruct-2509 supports up to 65,536 tokens of context. Our memory estimates use 8k, so long prompts need more memory than shown.

What does it cost through an API? We did not find a hosted API for this model.

License in plain English

Apache-2.0. This license permits commercial use, modification and redistribution, with conditions such as keeping the required notices. This summary is not legal advice.

Read Apache-2.0

Read about this license

OMHQ RigBench

Not yet tested. We show no speed or quality score without a measurement.

Revision history and sources

Last updated . Sources:Hugging Face model card, GGUF repository.