Can Laptop · GeForce RTX 4090 Laptop · 32 GB RAM run Step 5 Preview 600B-A27B?
16 GB VRAM + 32 GB RAM · 576 GB/s memory bandwidth · Step 5 Preview 600B-A27B has 600B parameters (27B active per token).
Short answer
No. This combination isn't supported.
Step 5 Preview 600B-A27B is not published in a format llama.cpp (llama-server) can load (GGUF).
The same applies to every workload we rate (chat, coding questions, coding in a repository, agentic coding and long documents): they all need at least as much memory as chat.
Other models for Laptop · GeForce RTX 4090 Laptop · 32 GB RAM
The best-rated models for chat on this machine.
- gpt-oss-20b100–170 tok/sExcellent
- Gemma 4 26B-A4B110–190 tok/sExcellent
- MiniCPM5 2B100–170 tok/sExcellent
- Qwen3.5 9B35–55 tok/sExcellent
- Qwen3.5 4B65–100 tok/sExcellent
- Gemma 4 12B30–45 tok/sExcellent
Cheapest machines for Step 5 Preview 600B-A27B
Hardware rated comfortable or better for chat, lowest price first.
No machine in our catalog runs it comfortably for chat.
Different tool, context size or workload?
These pages use typical settings. The full check models your exact setup.