GraySoft
Download guIDE →
Projects Models Compare Cloud benchmarks FAQ Download guIDE →

DeepSeek cloud models

38 models tracked via Artificial Analysis. Compare cloud performance, then find local GGUF versions in the GraySoft model catalog.

ModelIntelligenceSpeed (tok/s)
DeepSeek V4.1 Flash 1017 (Max)45.1212.377
DeepSeek V4.1 Flash (Max)39.5233.319
DeepSeek V4 Pro 0813 (Max)3695.868
DeepSeek V4 Flash Vision (Max)34.8200.149
DeepSeek V4 Flash 0731 (Max)34.30
DeepSeek V4 Pro 0424 (Max)30.40
DeepSeek V4 Pro 0424 (High)30.10
DeepSeek V4.1 Flash (Non-reasoning)24.7369.159
DeepSeek V4 Flash 0420 (High)24.40
DeepSeek V4 Flash 0420 (Max)24.20
DeepSeek V3.2 (Reasoning)21.50
DeepSeek V4 Pro 0424 (Non-reasoning)20.80
DeepSeek V4 Pro 0813 (Non-reasoning)20.496.375
DeepSeek V4 Flash 0420 (Non-reasoning)18.90
DeepSeek V3.2 Exp (Reasoning)16.60
DeepSeek V3.2 (Non-reasoning)160
DeepSeek V3.1 Terminus (Reasoning)14.80
DeepSeek V3.2 Speciale14.50
DeepSeek V3.1 Terminus (Non-reasoning)13.90
DeepSeek V3.2 Exp (Non-reasoning)13.90
DeepSeek V3.1 (Non-reasoning)13.70
DeepSeek V3.1 (Reasoning)13.50
DeepSeek R1 0528 (May '25)13.10
DeepSeek R1 (Jan '25)11.40
DeepSeek V3 03249.70
DeepSeek V3 (Dec '24)8.50
DeepSeek R1 Distill Qwen 32B8.40
DeepSeek R1 0528 Qwen3 8B8.10
DeepSeek R1 Distill Llama 70B7.90
DeepSeek R1 Distill Qwen 14B7.80
DeepSeek-V2.5 (Dec '24)6.60
DeepSeek-V2.56.60
DeepSeek R1 Distill Llama 8B6.50
DeepSeek-Coder-V260
DeepSeek R1 Distill Qwen 1.5B5.50
DeepSeek-V2-Chat5.50
DeepSeek Coder V2 Lite Instruct5.30
DeepSeek LLM 67B Chat (V1)5.30

Run models locally with guIDE

Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.

Download guIDE → · Browse 524k+ models · Compare models