DeepSeek R1 0528 Distill Qwen3 8B
Readymodel path:accounts/fireworks/models/deepseek-r1-0528-distill-qwen3-8b
We distilled the chain-of-thought from DeepSeek-R1-0528 to post-train Qwen3 8B Base, obtaining DeepSeek-R1-0528-Qwen3-8B. This model achieves state-of-the-art (SOTA) performance among open-source models on the AIME 2024, surpassing Qwen3 8B by +10.0% and matching the performance of Qwen3-235B-thinking.
On-demand deployments allow you to use DeepSeek R1 0528 Distill Qwen3 8B on dedicated GPUs with Fireworks' high-performance serving stack with high reliability and no rate limits.