Qwen on NVIDIA Blackwell

Can I run Qwen3 30B-A3B on an RTX 5080?

Not at Q4_K_M — it needs 18.8 GB against 14.2 GB available. Drop to IQ3_XXS and it fits, at about 143 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 5080 and the rest in system RAM, at roughly 46.2 tok/s — usable for batch work, painful for chat. A smaller quantisation or a shorter context is usually the better trade.

Generation46.2tok/s
Prompt processing7042tok/s
Max context0tokens
KV per 1K tokens0GB

Every quantisation of Qwen3 30B-A3B on a RTX 5080

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 — 7.67
INT8 / W8A8 8.50 30.1 GB 31.6 GB Won't fit — 17.4
Q8_0 (GGUF) 8.50 30.1 GB 31.6 GB Won't fit — 17.4
FP8 (E4M3) 8.00 28.4 GB 30.0 GB Won't fit — 18.7
Q6_K 6.56 23.3 GB 24.9 GB Won't fit — 25.8
Q5_K_M 5.67 20.2 GB 21.7 GB Won't fit — 33.4
Q5_K_S 5.52 19.6 GB 21.2 GB Won't fit — 35.4
Q4_K_M 4.85 17.3 GB 18.8 GB Won't fit — 46.2
Q4_K_S 4.58 16.3 GB 17.9 GB Won't fit — 53.0
Q4_0 4.55 16.2 GB 17.8 GB Won't fit — 53.2
AWQ 4-bit 4.25 16.0 GB 17.5 GB Won't fit — 56.7
GPTQ 4-bit 4.25 16.0 GB 17.5 GB Won't fit — 56.7
MXFP4 4.25 16.0 GB 17.5 GB Won't fit — 56.7
IQ4_XS 4.25 15.2 GB 16.7 GB Won't fit — 65.6
Q3_K_M 3.91 14.0 GB 15.5 GB Won't fit — 83.9
IQ3_M 3.70 13.3 GB 14.8 GB Won't fit 2K 101
IQ3_XXS 3.06 11.1 GB 12.6 GB Runs comfortably 26K 143
Q2_K 2.63 9.6 GB 11.1 GB Runs comfortably 42K 150
IQ2_XXS 2.06 7.6 GB 9.1 GB Runs comfortably 63K 159
IQ1_M 1.75 6.5 GB 8.0 GB Runs comfortably 74K 165

Also worth checking

Qwen3 30B-A3B on every GPU
Full hardware tableEverything that runs on a RTX 5080
Full model tableWhy the KV cache is the part that bites
Guide