Qwen on NVIDIA Blackwell

Can I run Qwen3 30B-A3B on an RTX 5060 Ti 16GB?

Not at Q4_K_M — it needs 18.8 GB against 14.2 GB available. Drop to IQ3_XXS and it fits, at about 97.1 tokens per second.

Won't fit

18.8 GB of 14.2 GB · 132%
020 GB
Weights 17.3 GB
KV cache 0.8 GB
Runtime overhead 0.8 GB
Over the limit 4.6 GB

Short by 4.6 GB. You can run it with 35 of 48 layers on the RTX 5060 Ti 16GB and the rest in system RAM, at roughly 39.8 tok/s — usable for batch work, painful for chat. A smaller quantisation or a shorter context is usually the better trade.

Generation39.8tok/s
Prompt processing2955tok/s
Max context0tokens
KV per 1K tokens0GB

Every quantisation of Qwen3 30B-A3B on a RTX 5060 Ti 16GB

Highlighted row is the highest quality that still fits at 8K context.

QuantisationbpwWeights TotalVerdictMax ctxtok/s
FP16 / BF16 16.00 56.9 GB 58.4 GB Won't fit 7.50
INT8 / W8A8 8.50 30.1 GB 31.6 GB Won't fit 16.5
Q8_0 (GGUF) 8.50 30.1 GB 31.6 GB Won't fit 16.5
FP8 (E4M3) 8.00 28.4 GB 30.0 GB Won't fit 17.7
Q6_K 6.56 23.3 GB 24.9 GB Won't fit 23.8
Q5_K_M 5.67 20.2 GB 21.7 GB Won't fit 30.0
Q5_K_S 5.52 19.6 GB 21.2 GB Won't fit 31.6
Q4_K_M 4.85 17.3 GB 18.8 GB Won't fit 39.8
Q4_K_S 4.58 16.3 GB 17.9 GB Won't fit 44.7
Q4_0 4.55 16.2 GB 17.8 GB Won't fit 44.9
AWQ 4-bit 4.25 16.0 GB 17.5 GB Won't fit 47.3
GPTQ 4-bit 4.25 16.0 GB 17.5 GB Won't fit 47.3
MXFP4 4.25 16.0 GB 17.5 GB Won't fit 47.3
IQ4_XS 4.25 15.2 GB 16.7 GB Won't fit 53.2
Q3_K_M 3.91 14.0 GB 15.5 GB Won't fit 64.5
IQ3_M 3.70 13.3 GB 14.8 GB Won't fit 2K 74.0
IQ3_XXS 3.06 11.1 GB 12.6 GB Runs comfortably 26K 97.1
Q2_K 2.63 9.6 GB 11.1 GB Runs comfortably 42K 104
IQ2_XXS 2.06 7.6 GB 9.1 GB Runs comfortably 63K 114
IQ1_M 1.75 6.5 GB 8.0 GB Runs comfortably 74K 120

Also worth checking