pd95/ apertus-mlx

9 1 week ago

Experimental MLX-backed Apertus 8B Instruct for custom Ollama builds. Requires ApertusForCausalLM support and is not compatible with the regular Ollama app.

tools thinking 8b 
ollama run pd95/apertus-mlx:8b

Applications

Claude Code
Claude Code ollama launch claude --model pd95/apertus-mlx:8b
Codex App
Codex App ollama launch codex-app --model pd95/apertus-mlx:8b
OpenClaw
OpenClaw ollama launch openclaw --model pd95/apertus-mlx:8b
Hermes Agent
Hermes Agent ollama launch hermes --model pd95/apertus-mlx:8b
Codex
Codex ollama launch codex --model pd95/apertus-mlx:8b
OpenCode
OpenCode ollama launch opencode --model pd95/apertus-mlx:8b

Models

View all →

2 models

apertus-mlx:8b

5.3GB · 64K context window · Text · 1 week ago

Readme

apertus-mlx

Experimental MLX-backed Ollama build of Apertus 8B Instruct.

This model requires a custom Ollama build with experimental MLX safetensors support and ApertusForCausalLM support. It will not run on the regular public Ollama app/build.

Tags

  • pd95/apertus-mlx:8b - recommended default, currently NVFP4
  • pd95/apertus-mlx:8b-nvfp4 - explicit NVFP4 artifact

Source

This model is an experimental Ollama/MLX conversion of:

https://huggingface.co/swiss-ai/Apertus-8B-Instruct-2509

Apertus 8B Instruct is released by the Swiss AI Initiative / Swiss National AI Institute.

Technical report:

https://arxiv.org/abs/2509.14233

License and Use Policy

Apertus is released under the Apache License 2.0:

https://huggingface.co/swiss-ai/Apertus-8B-Instruct-2509/blob/main/LICENSE.txt

Use is also subject to the Apertus LLM Acceptable Use Policy:

https://huggingface.co/swiss-ai/Apertus-8B-Instruct-2509/blob/main/USAGE_POLICY.md

This repository only republishes a quantized MLX/Ollama artifact. It does not change the upstream Apertus license or usage terms. Please review the upstream Apache-2.0 license and Apertus acceptable-use policy before use or redistribution.

Notes

  • Architecture: Apertus 8B Instruct
  • Quantization: NVFP4
  • Context window: 64K
  • Capabilities: text, tools, thinking
  • Runtime: experimental Ollama MLX runner

This model is intended for testing the experimental Apertus MLX path in Ollama.