Compare / DeepSeek-R1-0528-Qwen3-8B vs Apertus 1.5 8B

DeepSeek-R1-0528-Qwen3-8B vs Apertus 1.5 8B

Updated November 2026

Verdict

DeepSeek-R1-0528-Qwen3-8B scores higher on the Small LM Index: 53.1 vs 20.1. On the 1 benchmark both labs report, DeepSeek-R1-0528-Qwen3-8B wins 1 and Apertus 1.5 8B wins 0. Both need about 7.2 GB of memory at 4-bit quantization. Neither model has a hosted API on OpenRouter, so you would run both yourself.

Pick DeepSeek-R1-0528-Qwen3-8B if…

you want the strongest model overall
you want the more widely used model (more quantized builds and community support)

Pick Apertus 1.5 8B if…

you work with long documents
you need image input

Specifications

	DeepSeek-R1-0528-Qwen3-8B	Apertus 1.5 8B
Small LM Index	53.1 (likely 48–58)	20.1 (likely 15–28)
Lab	DeepSeek · China	Swiss AI Initiative (Apertus) · Europe
Released	2025-05-29	2026-07-24
Parameters	8.2B (dense)	8.9B (dense)
Memory at 4-bit	~6.8 GB	~7.2 GB
Context window	128K tokens	262K tokens
Input	text	text, image, audio
Reasoning	Always thinks	Hybrid (thinking on/off)
License	MIT	Apache-2.0
API price / 1M tokens	Self-host only	Self-host only
Hugging Face downloads (30 days)	357.7K	42K

Benchmarks

Higher is better. Bold marks the winner where both labs report a score. ≈ marks the index model's estimate for a score that wasn't reported, ✓ an independent measurement and * a score measured by another lab.

Benchmark	DeepSeek-R1-0528-Qwen3-8B	Apertus 1.5 8B
MMLU-Pro Knowledge	≈ 74	48.8
GPQA Diamond Knowledge	61.1	27.2
AIME Math	76.3	≈ 16
LiveCodeBench Coding	60.5	≈ 20

Scores are mostly reported by each lab with its own settings, so small gaps are noise. See the methodology. Open in the interactive comparison to add more models.

Questions

Which is better, DeepSeek-R1-0528-Qwen3-8B or Apertus 1.5 8B?

DeepSeek-R1-0528-Qwen3-8B scores higher on the Small LM Index: 53.1 vs 20.1. On the 1 benchmark both labs report, DeepSeek-R1-0528-Qwen3-8B wins 1 and Apertus 1.5 8B wins 0.

Which is cheaper to run?

Neither model has a hosted API on OpenRouter, so you would run both yourself. Both need about 7.2 GB of memory at 4-bit quantization.

Which has the longer context window?

Apertus 1.5 8B has the longer context window: 262K tokens against 128K.

Can I use DeepSeek-R1-0528-Qwen3-8B and Apertus 1.5 8B commercially?

DeepSeek-R1-0528-Qwen3-8B is released under MIT and Apertus 1.5 8B under Apache-2.0. Apache 2.0 and MIT allow commercial use; other licenses can add conditions, so read the license before shipping a product.