Qwen3 30B-A3B at Q4_K_M needs about 19.7 GB, more than the 16 GB of the RTX 4080: part of the model runs from system RAM, which slows generation. At Q3_K_M it fits entirely.
Q4_K_M · 8K context
The model needs about 19.7 GB but only 15.5 GB of VRAM is usable: 4.2 GB must be loaded into system RAM. It runs, 79% on the GPU, but more slowly.
~19.7 GB (19.1 GB–20.5 GB) needed · estimate
4.2 GB must be offloaded to system RAM
EstimateData updated 24 days agoSource: Run LLM Locally engine, Hugging Face config.json + model card
What makes this estimate less reliable
| Qwen3 30B-A3B Q8_08K~33.4 GB · 8.5–17 tok/s estimate | Possible but slow |
|---|---|
| Qwen3 30B-A3B Q6_K8K~26.1 GB · 14–26 tok/s estimate | CPU/GPU offload |
| Qwen3 30B-A3B Q5_K_M8K~22.8 GB · 18–36 tok/s estimate | CPU/GPU offload |
| Qwen3 30B-A3B Q4_K_M8K~19.7 GB · 27–54 tok/s estimate | CPU/GPU offload |
| Qwen3 30B-A3B IQ4_XS8K~17.7 GB · 41–83 tok/s estimate | CPU/GPU offload |
| Qwen3 30B-A3B Q3_K_M8K~15.4 GB · 118–195 tok/s estimate | Compatible with limits |
Prices and links follow the market you choose.
AMD
CompatibleRuns Qwen3 30B-A3B Q4_K_M entirely in memory
Unified memory PC
ExcellentRuns Qwen3 30B-A3B Q4_K_M entirely in memory
Lowest memory tier
CompatibleRuns Qwen3 30B-A3B Q4_K_M entirely in memory
No current offer imported for this market: the link opens a marketplace search.
