MiniMax-M1-80k ↗
- source model id
- MiniMaxAI/MiniMax-M1-80k
- hosting
- siliconflow-hosted
- platforms
- SiliconFlow
- max output tokens
- 131072
- architecture
- input_modalities
- text
- output_modalities
- text
- capabilities
MiniMax-M1 is a open-weight, large-scale hybrid-attention reasoning model with 456 B parameters and 45.9 B activated per token. It natively supports 1 M-token context, lightning attention enabling 75…
siliconFlow/MiniMaxAI/MiniMax-M1-80k
MiniMax-M1 is a open-weight, large-scale hybrid-attention reasoning model with 456 B parameters and 45.9 B activated per token. It natively supports 1 M-token context, lightning attention enabling 75% FLOPs savings vs DeepSeek R1 at 100 K tokens, and leverages a MoE architecture. Efficient RL training with CISPO and hybrid design yields state-of-the-art performance on long-input reasoning and real-world software engineering tasks.
1–1 / 1
1–1 / 1
14 / 100
1–2 / 2
1–8 / 8
Hugging Face · Model repository ↗
1–3 / 3
These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.