pd95/ apertus-mlx:8b-bf16-v0.32.15-r2

176 1 month ago

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

tools 8b 
ollama run pd95/apertus-mlx:8b-bf16-v0.32.15-r2

Details

1 month ago

7fda387a5932 · 16GB

json
{ "architectures": [ "ApertusForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "bos
json
{ "_from_model_config": true, "bos_token_id": 1, "eos_token_id": [2, 68, 72], "transformers_version"
json
{ "bos_token": { "content": "<s>", "lstrip": false, "normalized": false, "rstrip": false, "single_wo
json
{ "version": "1.0", "truncation": null, "padding": null, "added_tokens": [ { "id": 0, "content": "<u
json
{ "add_bos_token": true, "add_eos_token": false, "add_prefix_space": false, "added_tokens_decoder":
license
Copyright 2025 - The Swiss AI team. Apache License Version 2.0, January 2004 http://www.apache.org/l
params
{ "stop": [ "</s>", "<|assistant_end|>", "<|tools_suffix|>" ], "
template
{{ .Prompt }}
451 tensors

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.

The artifacts require an Apertus-capable custom MLX preview. Their stored numeric compatibility requirement is Ollama 0.25.0-rc0: the exact release artifacts were tested successfully from the first Apertus preview through v0.32.15-r2. Use v0.32.15-r2 or newer for correct capability reporting and rejection of unsupported thinking requests.

If you are ready to install a custom Ollama build, visit https://www.doapp.ch/Ollama/.

Tags

  • pd95/apertus-mlx:8b — recommended default, currently NVFP4
  • pd95/apertus-mlx:8b-nvfp4 — explicit NVFP4 artifact
  • pd95/apertus-mlx:8b-mxfp8 — larger packed-MXFP8 artifact
  • pd95/apertus-mlx:8b-bf16 — unquantized BF16 artifact

Immutable release tags:

  • pd95/apertus-mlx:8b-nvfp4-v0.32.15-r2
  • pd95/apertus-mlx:8b-mxfp8-v0.32.15-r2
  • pd95/apertus-mlx:8b-bf16-v0.32.15-r2

Source

This model is an experimental Ollama/MLX conversion of:

https://huggingface.co/swiss-ai/Apertus-8B-Instruct-2509/tree/50761a511195fde9d958f62f3b6344329d4bd191

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
  • Source revision: 50761a511195fde9d958f62f3b6344329d4bd191
  • Available formats: NVFP4, packed MXFP8, and BF16
  • Context window: 64K
  • Capabilities: text, tools
  • Thinking: not supported by Apertus 1.0
  • Runtime: experimental Ollama MLX runner
  • Import preview: v0.32.15-r2
  • Tested execution floor: v0.25.0-rc0
  • Recommended MLX preview: v0.32.15-r2 or newer

The v0.32.15-r2 artifacts correct the stored Apertus family and capability metadata. In particular, they no longer advertise thinking support. The NVFP4 artifact also contains updated tensor content; the packed MXFP8 and BF16 tensor content remains equivalent to the previous published variants, but those artifacts still require replacement for the metadata, license, and compatibility corrections.

Older Apertus previews can execute these artifacts, but they may dynamically report duplicate tool support and the unsupported thinking capability. That is a runtime metadata issue; it does not change the tested artifact execution floor above.

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