Model Intelligence Sheet
1bit-MONSTER/Apertus-8B-Instruct-2509-GGUF overview
Apertus 8B Instruct 2509 — GGUF Q4 K M Unsloth's Q4 K M GGUF for Apertus Swiss AI's fully open training data model , re hosted with measured performance for th…
Runs locally from ~4.71 GB disk (8 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
1 GGUF files detected
Direct downloads for local inference
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| Apertus-8B-Instruct-2509-Q4_K_M.gguf | GGUF | Q4_K_M | 4.71 GB | Download |
Model Details
| Model ID | 1bit-MONSTER/Apertus-8B-Instruct-2509-GGUF |
|---|---|
| Author | 1bit-MONSTER |
| Pipeline | — |
| License | apache-2.0 |
| Base model | swiss-ai/Apertus-8B-Instruct-2509 |
| Last modified | 2026-09-26T15:46:06.000Z |
Model README
---
license: apache-2.0
base_model:
- swiss-ai/Apertus-8B-Instruct-2509
tags:
- gguf
---
Apertus-8B-Instruct-2509 — GGUF (Q4_K_M)
Unsloth's Q4_K_M GGUF for Apertus (Swiss AI's fully-open-training-data model), re-hosted
with measured performance for the 1bit engine
on Strix Halo.
Contents
Apertus-8B-Instruct-2509-Q4_K_M.gguf
Measured performance (Strix Halo, Vulkan)
pp512: 1152 tok/s · tg128: 39.7 tok/s
Running it
1bit serve -m Apertus-8B-Instruct-2509-Q4_K_M.gguf --device vulkanAttribution
- Model: swiss-ai/Apertus-8B-Instruct-2509, Apache 2.0.
- Quantization: unsloth/Apertus-8B-Instruct-2509-GGUF.
- License: Apache 2.0, inherited from the base model.
Run 1bit-MONSTER/Apertus-8B-Instruct-2509-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models