With 24 GB of VRAM, the Tesla P40 runs Qwen3 30B-A3B at Q4_K_M entirely on the GPU with an 8K context (about 19.7 GB needed). At Q8_0 it does not fit in VRAM.
Q4_K_M · 8K context
The model needs about 19.7 GB and fits in the 23.3 GB available, with 3.5 GB to spare.
~19.7 GB (19.1 GB–20.5 GB) needed · estimate
Fits entirely in VRAM · 3.5 GB left
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 · 13–24 tok/s estimate | CPU/GPU offload |
|---|---|
| Qwen3 30B-A3B Q6_K8K~26.1 GB · 26–49 tok/s estimate | CPU/GPU offload |
| Qwen3 30B-A3B Q5_K_M8K~22.8 GB · 60–88 tok/s estimate | Compatible with limits |
| Qwen3 30B-A3B Q4_K_M8K~19.7 GB · 66–98 tok/s estimate | Excellent |
| Qwen3 30B-A3B IQ4_XS8K~17.7 GB · 71–106 tok/s estimate | Excellent |
| Qwen3 30B-A3B Q3_K_M8K~15.4 GB · 77–117 tok/s estimate | Excellent |
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.
