Can I run it?
Can I run Qwen2.5 32B Instruct on GeForce RTX 4090?
Tight fit
Tight fit fully on your GeForce RTX 4090 at Q4_K_M, 8K context, about 25–34 tok/s. Weights 18.5 GB plus 2.00 GB of KV cache — 21.0 GB of 22.3 GB usable.
Best quantQ4_K_M
Working context8K
Max that fits8K
Speed25–34 tok/s
Weights18.5 GB
KV cache2.00 GB
Total21.0 GB
Usable22.3 GB
Qwen2.5 32B Instruct details · GeForce RTX 4090 page · How this estimate is made
Run commands
llama.cpp
llama-server -hf bartowski/Qwen2.5-32B-Instruct-GGUF:Q4_K_M -c 8192 -ngl 64
Ollama
ollama run qwen2.5
LM Studio
lms get bartowski/Qwen2.5-32B-Instruct-GGUF # Then load quant Q4_K_M
Assumptions
- Estimate, not a benchmark. Decode speed uses a memory-bandwidth model at 55–75% of peak.
- KV cache is FP16. Engine overhead assumes llama.cpp (0.3 GB + 1% of the weights). Ollama is closer to 0.9 GB + 3%, LM Studio closer to 1 GB + 3%.
- Q4_K_M size is the real GGUF file size from Hugging Face.
- 0.5 GB is reserved because this GPU also drives a display, then 5% of the rest is left free.
- Speed is quoted at 8K context, not at the maximum context that still fits.
Larger models that also fit
- Can I run Qwen3.6 35B A3B on GeForce RTX 4090? — Tight fit, UD-Q4_K_XL, 264–359 tok/s
- Can I run Qwen3.8 35B A3B Distill on GeForce RTX 4090? — Tight fit, Q4_K_M, 277–378 tok/s
- Can I run Qwen3.5 35B A3B on GeForce RTX 4090? — Tight fit, UD-Q4_K_XL, 265–361 tok/s
Updated 2026-10-17. Profile on this page is the device default plus 32 GB of DDR5-5600 system RAM.