Can I run it?
Can I run Swift Qwen3.8 27B on GeForce RTX 5090?
Tight fit
Tight fit fully on your GeForce RTX 5090 at Q8_0, 8K context, about 33–45 tok/s. Weights 27.1 GB plus 0.57 GB of KV cache — 28.3 GB of 29.9 GB usable. Up to 16K context still fits.
Best quantQ8_0
Working context8K
Max that fits16K
Speed33–45 tok/sEstimate from memory bandwidth, not a benchmark. Method.
Weights27.1 GB
KV cache0.57 GB
Total28.3 GB
Usable29.9 GB
Swift Qwen3.8 27B details · GeForce RTX 5090 page · How this estimate is made
Run commands
llama.cpp
llama-server -hf ukisai/Swift-Qwen3.8-27B-GGUF:Q8_0 -c 8192 -ngl 64
No matching name in the Ollama library snapshot.
LM Studio
lms get ukisai/Swift-Qwen3.8-27B-GGUF # Then load quant Q8_0
Assumptions
- Estimate from memory bandwidth, not a benchmark. Decode speed uses 55–75% of peak bandwidth.
- 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%.
- Q8_0 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 Qwen3.8 27B on GeForce RTX 5090? — Tight fit, UD-Q8_K_L, 34–47 tok/s (estimate)
- Can I run Qwen3.6 35B A3B on GeForce RTX 5090? — Tight fit, UD-Q6_K, 81–111 tok/s (estimate)
- Can I run Qwen3.8 35B A3B Distill on GeForce RTX 5090? — Tight fit, Q6_K, 82–111 tok/s (estimate)
Updated 2026-10-24. Profile on this page is the device default plus 32 GB of DDR5-5600 system RAM.