swiss-ai / text-generation updated 2 weeks ago

Apertus-8B-Instruct-2509

Name: Apertus-8B-Instruct-2509
Author: swiss-ai

1. Model Summary 2. How to use 3. Evaluation 4. Training 5. Limitations 6. Legal Aspects

Params

8.1 B

Context

65,536

Downloads 30d

361 K

Likes

484

Commercial use: allowed apache-2.0 Not gated SAFETENSORS View on Hugging Face ↗

Download history

daily snapshots · 10 days

361 K297 K

Jul 28Jul 31Aug 3Aug 6

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
model.safetensors	bf16	16.1 GB	19.4 GB	✅ Runs comfortably
model.safetensors (bf16, full)	bf16 + 64K ctx	16.1 GB	27.9 GB	❌ Won’t fit

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Run it

copy-paste, exact tags checked against the Hub

~ · curl · api/v1

$ curl -s https://aimodelscomparison.com/api/v1/models/apertus-8b-instruct-2509
{
  "hf_id": "swiss-ai/Apertus-8B-Instruct-2509",
  "params_b": 8.05,
  "context_length": 65536,
  "license": { "id": "apache-2.0", "commercial": "yes" },
  "downloads_30d": 360741,
  "vram_estimates": [
    { "quant": "bf16", "gb": 19.4 }
  ],
  "updated_at": "2026-07-28T18:06:44Z"
}

est. VRAM —on RTX 4090 · 24 GBJSON API →

Specifications

Architecture: ApertusForCausalLM
Parameters: 8.1 B
Tensor type: BF16
Context length: 65,536
Vocabulary: 131,072
Layers / heads: 32 / 32
Licence: apache-2.0
First seen on the Hub: 2025-08-13
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Compare with

Qwen3-8B 16.3 M Qwen2.5-7B-Instruct 12.1 M Qwen3.6-35B-A3B-NVFP4 11.3 M Llama-3.1-8B-Instruct 8.0 M Qwen2.5-7B-Instruct-AWQ 4.6 M granite-4.1-8b 4.2 M

Appears in

Best open coding models Commercial-use text models Models that fit in 12 GB