LLMs ·

Apertus v1.5 70B

Parameters
72B
Architecture
Dense
Max context
256K tokens
License
apache-2.0
Released
2026-07

How to run it

Original weights · Hugging Face

Full-precision files from Swiss AI, for fine-tuning, vLLM, Transformers.

huggingface.co/swiss-ai/Apertus-v1.5-70B (opens in a new tab)

Free Hugging Face account needed: accept the license on the model page and the download starts right away.

Links checked 3 days ago against Hugging Face, Ollama and GitHub.

Apps that run Apertus v1.5 70B

Our pick for each kind of computer, assuming the model fits in its memory. Pick your own GPU or device in the Model Finder for an exact answer.

Mac (Apple silicon)

Docker Model Runner

Handy if you already work in Docker.

Also good:

Windows PC, NVIDIA GPU

Docker Model Runner

Handy if you already work in Docker.

Also good:

Windows PC, AMD Radeon

Docker Model Runner

Handy if you already work in Docker.

Also good:

Linux, NVIDIA GPU

Docker Model Runner

Handy if you already work in Docker.

Also good:

Linux server, 80 GB+ GPUs

vLLM

The full model fits in GPU memory at 8-bit, so it can batch many requests: best for serving a team or an app.

Also good:

App Type Opens it as Systems Engine Start
vLLM Server Original weights WSLWindowsLinux vLLM 
vllm serve swiss-ai/Apertus-v1.5-70B
SGLang Server Original weights WSLWindowsLinux SGLang 
python3 -m sglang.launch_server --model-path swiss-ai/Apertus-v1.5-70B
Docker Model Runner CLI + API Original weights macOSWindowsLinux llama.cpp, vLLM 
docker model run hf.co/swiss-ai/Apertus-v1.5-70B
Text Generation WebUI Desktop app Original weights macOSWindowsLinux llama.cpp, Transformers, ExLlamaV3 Get Text Generation WebUI

Which apps can open a model depends on the files published for it: GGUF for llama.cpp-based apps, MLX for Apple’s engine, the original weights for vLLM and SGLang. Compare every app.

Memory needed

Weights plus KV cache and runtime overhead. Leave a little extra free for the operating system and other apps. Try another context length.

Quantization Quality Weights Total at 8K context Total at 32K context Download
Q2_K Low 28.8 GB 32.1 GB 40.1 GB All files (opens in a new tab)
Q3_K_M Low 35.3 GB 38.6 GB 46.6 GB All files (opens in a new tab)
Q4_K_M Good 43.9 GB 47.2 GB 55.3 GB All files (opens in a new tab)
Q5_K_M High 51.1 GB 54.4 GB 62.5 GB All files (opens in a new tab)
Q6_K High 59.0 GB 62.3 GB 70.4 GB All files (opens in a new tab)
Q8_0 Very high 76.3 GB 79.6 GB 87.7 GB All files (opens in a new tab)
F16 Full 144 GB 147 GB 155 GB Original weights (opens in a new tab)

Best hardware for Apertus v1.5 70B

The least expensive GPU in our catalog that runs it without offloading is the AMD Radeon PRO W7800 48GB (launch price $2,799) at Q3_K_M.

Quality Hardware Quant Memory Speed Runs
62Good quality (B) · 62 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA RTX PRO 6000 Blackwell Workstation EditionNVIDIA RTX PRO 6000 Blackwell Q4_K_M 52.0 GB / 96.0 GB 30.5 tok/s Runs great
55Good quality (B) · 55 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. Apple MacBook Pro (14-inch, M4 Pro or M4 Max, 2024)Apple M4 Max (64 GB) Q3_K_M 42.4 GB / 48.0 GB 10.4 tok/s Runs welltight fit
62Good quality (B) · 62 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. Apple Mac Studio (2023) (M2 Max or M2 Ultra)Apple M2 Ultra (192 GB) Q4_K_M 58.7 GB / 144 GB 11.7 tok/s Runs well
62Good quality (B) · 62 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. Apple Mac Studio (2025) (M4 Max or M3 Ultra)Apple M3 Ultra (256 GB) Q4_K_M 62.6 GB / 192 GB 12.0 tok/s Runs well
55Good quality (B) · 55 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. Apple MacBook Pro (14-inch, M4 Pro or M4 Max, 2024)Apple M4 Max (128 GB) Q3_K_M 46.2 GB / 96.0 GB 10.4 tok/s Runs well
62Good quality (B) · 62 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. Apple Mac Studio (2025) (M4 Max or M3 Ultra)Apple M3 Ultra (512 GB) Q4_K_M 77.9 GB / 384 GB 12.0 tok/s Runs well
46Fair quality (C) · 46 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5090 Founders EditionNVIDIA GeForce RTX 5090 Q2_K 33.7 GB / 32.0 GB 19.9 tok/s Runs welloffloads to RAM
65Good quality (B) · 65 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GH200 Grace Hopper (96 GB GPU)NVIDIA GH200 Grace Hopper (96 GB GPU) Q6_K 67.1 GB / 96.0 GB 47.3 tok/s Runs great
65Good quality (B) · 65 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA H100 NVLNVIDIA H100 NVL Q6_K 67.0 GB / 94.0 GB 46.1 tok/s Runs great
65Good quality (B) · 65 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA H20 Q6_K 67.1 GB / 96.0 GB 47.3 tok/s Runs great

Check it on your own hardware

Run it on a cluster

Devices that can’t run Apertus v1.5 70B alone can run it together. These example clusters do:

Try it with your own devices

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.

Was this page helpful?