DeepSeek R1 0528 Qwen3 8B
DeepSeek-R1-0528 is a lightly upgraded release of DeepSeek R1 that taps more compute and smarter post-training tricks, pushing its reasoning and inference to the brink of flagship models like O3 and Gemini 2.5 Pro. It now tops math, programming, and logic leaderboards, showcasing a step-change in depth-of-thought.
Input
Output
Context
128K
Max Output
32K
Parameters
8B
Technical Specifications
Model TypeChat
Context Window128K
Max Output Tokens32K
Parameters8B
Training Cutoff—
Licensemit
Capabilities
Input Modalities
text
Output Modalities
text
Features
code_generationfunction_callingjson_modereasoningstreamingtext_generation
Benchmarks
5.6%
HLE
65.0%
AIME
61.2%
GPQA
20.4%
SciCode
93.2%
MATH 500
73.9%
MMLU Pro
63.7
Math
7.7
Coding
51.3%
LiveCodeBench
16.4
Intelligence
50.0
Speed (tok/s)
41.4
TTFA (s)
1.4
TTFT (s)
Resources & Links
Estimated GPU Requirements for DeepSeek R1 0528 Qwen3 8B
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
Related Tools
Data sourced from official provider APIs and documentation
Last updated: May 5, 2026
Start building with the right model.
From model selection to production, one platform, no fragmentation.