llmrun

Qwen3 30B A3B vs QwQ 32B

QwQ 32B leads llmrun Score 96.2 to 93.9 (ranges overlap); both fit 24 GB at Q4_K_M; Qwen3 30B A3B is 5.4× faster on RTX 4090 (~173 vs ~32 tok/s).

Model A · Alibaba

Qwen3 30B A3B
93.9llmrun Score

30.5B · 3.4B active · 40K context · Apache 2.0 · Apr 2025

ChatFunctions

Model B · Alibaba

QwQ 32B
96.2llmrun Score

32.8B · 40K context · Apache 2.0 · Mar 2025

ChatReasoningFunctions

Which should you choose?

Choose Qwen3 30B A3B if you want…

  • Fits a 16 GB GPU

    Q3_K_M · 16 GB; QwQ 32B needs 13.6 GB at its smallest quant

  • 5.4× faster on RTX 4090

    ~173 vs ~32 tok/s

Choose QwQ 32B if you want…

  • Higher llmrun Score

    96.2 vs 93.9, ranges overlap

  • Also does reasoning

    Qwen3 30B A3B doesn't list it

On your hardware

Each model at its default quant (Q4_K_M), a smaller one when it must. Estimates, ±20%.

8 GB

RTX 4060 · 8 GB tier

Qwen3 30B A3B

Doesn't fit

smallest quant needs 9.5 GB

QwQ 32B

Doesn't fit

smallest quant needs 13.6 GB

12 GB

RTX 3060 12GB · 12 GB tier

Qwen3 30B A3B

IQ2_M · ~130 tok/s

11.4 GB · up to 16Kfits

QwQ 32B

Doesn't fit

smallest quant needs 13.6 GB

16 GB

RTX 5060 Ti 16GB · 16 GB tier

Qwen3 30B A3B

Q3_K_M · ~119 tok/s

16 GB · up to 16Kbetter quant

QwQ 32B

IQ2_M · ~25 tok/s

15.7 GB · up to 16K

24 GBreference

RTX 4090 · 24 GB tier

Qwen3 30B A3B

Q4_K_M · ~173 tok/s

19.4 GB · up to 40Kmore headroom

QwQ 32B

Q4_K_M · ~32 tok/stight

24.3 GB · up to 8K

32 GB

RTX 5090 · 32 GB tier

Qwen3 30B A3B

Q4_K_M · ~227 tok/s

19.4 GB · up to 40Kfaster

QwQ 32B

Q4_K_M · ~57 tok/s

24.3 GB · up to 40K

48 GB

RTX A6000 · 48 GB tier

Qwen3 30B A3B

Q4_K_M · ~148 tok/s

19.4 GB · up to 40Kfaster

QwQ 32B

Q4_K_M · ~24 tok/s

24.3 GB · up to 40K

Mac 32 GB

Mac Mini M4 · Macs

Qwen3 30B A3B

Q4_K_M · ~29 tok/s

19.4 GB · up to 40Kfaster

QwQ 32B

Q4_K_M · ~4 tok/s

24.3 GB · up to 16K

Mac 64 GB

Mac Studio M4 Max · Macs

Qwen3 30B A3B

Q4_K_M · ~67 tok/s

19.4 GB · up to 40Kfaster

QwQ 32B

Q4_K_M · ~19 tok/s

24.3 GB · up to 40K

Mac 128 GB

Mac Studio M4 Max · Macs

Qwen3 30B A3B

Q4_K_M · ~67 tok/s

19.4 GB · up to 40Kfaster

QwQ 32B

Q4_K_M · ~19 tok/s

24.3 GB · up to 40K

Reference GPU: RTX 4090. Tinted cell = the better pick on that machine (fits, more headroom, or at least 10% faster).

llmrun Score

with its 90% range · bars share one scale

Overall

Qwen3 30B A3B

93.991–97

QwQ 32B

96.293–99

Reasoning

Qwen3 30B A3B

83.775–93

QwQ 32B

no data

Qwen3 30B A3B · #68 of 100 open models · #17 of 35 that fit 24 GB

QwQ 32B · #64 of 100 open models · #16 of 35 that fit 24 GB

Benchmarks

3 shared boards: Qwen3 30B A3B leads 1, QwQ 32B leads 2 · Benchmarks imported Oct 2026

GPQA Diamond

Qwen3 30B A3B

61.7%#41/98 open

IndependentEpoch AI · Apr 2025

QwQ 32B

65.3%#38/98 open

IndependentEpoch AI · Mar 2025

AIME 2024/2025

Qwen3 30B A3B

62.8%#35/86 open

IndependentEpoch AI · Apr 2025

QwQ 32B

59.2%#38/86 open

IndependentEpoch AI · Mar 2025

Fiction.LiveBench

Qwen3 30B A3B

40.6%#21/25 open

IndependentEpoch AI · Apr 2025

QwQ 32B

83.3%#3/25 open

IndependentEpoch AI · Mar 2025

6 more boards (other shared and single-model boards)
LMArena Text

Qwen3 30B A3B

1326.7#90/187 open

ArenaLMArena · Oct 2026

QwQ 32B

1335.6#85/187 open

ArenaLMArena · Oct 2026

Only Qwen3 30B A3B (3)

Only QwQ 32B (2)

VRAM by quantization

Memory to load the model and 2K context; below it, the total at 32K and 128K context. Lighter side in bold.

Q2_K

Qwen3 30B A3B

13.4 GB11.3 GB file

32K 14.9 GB · 128K —

QwQ 32B

14.8 GB12.3 GB file

32K 22.8 GB · 128K —

Q3_K_S

Qwen3 30B A3B

13.8 GB13.3 GB file

32K 15.3 GB · 128K —

QwQ 32B

15.2 GB14.4 GB file

32K 23.2 GB · 128K —

Q3_K_M

Qwen3 30B A3B

15.3 GB14.7 GB file

32K 16.8 GB · 128K —

QwQ 32B

16.8 GB15.9 GB file

32K 24.9 GB · 128K —

Q4_0

Qwen3 30B A3B

15.7 GB17.4 GB file

32K 17.2 GB · 128K —

QwQ 32B

17.2 GB18.7 GB file

32K 25.3 GB · 128K —

Q4_K_M

Qwen3 30B A3B

18.7 GB18.6 GB file

32K 20.2 GB · 128K —

QwQ 32B

20.5 GB19.9 GB file

32K 28.6 GB · 128K —

Q5_K_M

Qwen3 30B A3B

22.2 GB21.7 GB file

32K 23.7 GB · 128K —

QwQ 32B

24.2 GB23.3 GB file

32K 32.2 GB · 128K —

Q6_K

Qwen3 30B A3B

25.6 GB25.1 GB file

32K 27.1 GB · 128K —

QwQ 32B

27.9 GB26.9 GB file

32K 35.9 GB · 128K —

Q8_0

Qwen3 30B A3B

30.9 GB32.5 GB file

32K 32.4 GB · 128K —

QwQ 32B

33.6 GB34.8 GB file

32K 41.7 GB · 128K —

20 more quants

IQ2_XXS

Qwen3 30B A3B

8.8 GB10.4 GB file

32K 10.3 GB · 128K —

QwQ 32B

9.9 GB9.0 GB file

32K 17.9 GB · 128K —

IQ2_XS

Qwen3 30B A3B

9.6 GB9.1 GB file

32K 11.1 GB · 128K —

QwQ 32B

10.7 GB10.0 GB file

32K 18.7 GB · 128K —

IQ2_S

Qwen3 30B A3B

9.9 GB9.2 GB file

32K 11.5 GB · 128K —

QwQ 32B

11.1 GB10.4 GB file

32K 19.1 GB · 128K —

IQ2_M

Qwen3 30B A3B

10.7 GB10.9 GB file

32K 12.2 GB · 128K —

QwQ 32B

11.9 GB11.3 GB file

32K 19.9 GB · 128K —

IQ3_XXS

Qwen3 30B A3B

12.2 GB12.9 GB file

32K 13.7 GB · 128K —

QwQ 32B

13.5 GB12.8 GB file

32K 21.6 GB · 128K —

Q2_K_S

Qwen3 30B A3B

not listed

QwQ 32B

13.9 GB11.5 GB file

32K 22.0 GB · 128K —

IQ3_XS

Qwen3 30B A3B

13.0 GB12.7 GB file

32K 14.5 GB · 128K —

QwQ 32B

14.4 GB13.7 GB file

32K 22.4 GB · 128K —

IQ3_S

Qwen3 30B A3B

13.4 GB14.0 GB file

32K 14.9 GB · 128K —

QwQ 32B

14.8 GB14.4 GB file

32K 22.8 GB · 128K —

IQ3_M

Qwen3 30B A3B

14.1 GB14.1 GB file

32K 15.7 GB · 128K —

QwQ 32B

15.6 GB14.8 GB file

32K 23.6 GB · 128K —

Q3_K_L

Qwen3 30B A3B

16.1 GB15.9 GB file

32K 17.6 GB · 128K —

QwQ 32B

17.6 GB17.2 GB file

32K 25.7 GB · 128K —

IQ4_XS

Qwen3 30B A3B

16.8 GB16.4 GB file

32K 18.3 GB · 128K —

QwQ 32B

18.5 GB17.7 GB file

32K 26.5 GB · 128K —

IQ4_NL

Qwen3 30B A3B

17.6 GB17.3 GB file

32K 19.1 GB · 128K —

QwQ 32B

19.3 GB18.7 GB file

32K 27.3 GB · 128K —

Q4_1

Qwen3 30B A3B

17.6 GB19.2 GB file

32K 19.1 GB · 128K —

QwQ 32B

19.3 GB20.6 GB file

32K 27.3 GB · 128K —

Q4_K_S

Qwen3 30B A3B

17.6 GB17.5 GB file

32K 19.1 GB · 128K —

QwQ 32B

19.3 GB18.8 GB file

32K 27.3 GB · 128K —

Q4_K_L

Qwen3 30B A3B

19.1 GB18.9 GB file

32K 20.6 GB · 128K —

QwQ 32B

20.9 GB20.4 GB file

32K 29.0 GB · 128K —

Q5_0

Qwen3 30B A3B

19.5 GB21.1 GB file

32K 21.0 GB · 128K —

QwQ 32B

21.3 GB22.6 GB file

32K 29.4 GB · 128K —

Q5_1

Qwen3 30B A3B

not listed

QwQ 32B

23.4 GB24.6 GB file

32K 31.4 GB · 128K —

Q5_K_S

Qwen3 30B A3B

21.4 GB21.1 GB file

32K 22.9 GB · 128K —

QwQ 32B

23.4 GB22.6 GB file

32K 31.4 GB · 128K —

Q5_K_L

Qwen3 30B A3B

22.5 GB21.9 GB file

32K 24.1 GB · 128K —

QwQ 32B

24.6 GB23.7 GB file

32K 32.6 GB · 128K —

BF16

Qwen3 30B A3B

61.5 GB61.1 GB file

32K 63.0 GB · 128K —

QwQ 32B

66.4 GB65.5 GB file

32K 74.4 GB · 128K —

How to run each

Specifications

Specifications of Qwen3 30B A3B and QwQ 32B
SpecQwen3 30B A3BQwQ 32B
PublisherAlibabaAlibaba
Parameters30.5B32.8B
Active parameters3.4B per token—
ArchitectureQwen3MoeForCausalLMQwen2ForCausalLM
Context40K tokens40K tokens
ModalitiesChat, Function-callingChat, Reasoning, Function-calling
LicenseApache 2.0Apache 2.0
ReleasedApr 2025Mar 2025

Frequently Asked Questions

Which is better, Qwen3 30B A3B or QwQ 32B?

QwQ 32B leads llmrun Score 96.2 to 93.9 (ranges overlap); both fit 24 GB at Q4_K_M; Qwen3 30B A3B is 5.4× faster on RTX 4090 (~173 vs ~32 tok/s). Choose Qwen3 30B A3B for fits a 16 GB GPU and 5.4× faster on RTX 4090; choose QwQ 32B for higher llmrun Score and also does reasoning.

Which needs less VRAM, Qwen3 30B A3B or QwQ 32B?

At Q4_K_M, Qwen3 30B A3B requires 18.7 GB while QwQ 32B needs 20.5 GB, making Qwen3 30B A3B the easier model to run on your local setup.

Which is faster on RTX 4090?

Estimated decode speed on RTX 4090 is about 173 tok/s for Qwen3 30B A3B (Q4_K_M) and 32 tok/s for QwQ 32B (Q4_K_M), so Qwen3 30B A3B is faster. Estimates, ±20%.

Can I run Qwen3 30B A3B or QwQ 32B on a 16 GB GPU?

Qwen3 30B A3B fits at Q3_K_M; QwQ 32B fits at IQ2_M.

Which has a longer context window, Qwen3 30B A3B or QwQ 32B?

Qwen3 30B A3B supports 40,960 tokens and QwQ 32B supports 40,960 tokens.

Qwen3 30B A3B vs QwQ 32B — VRAM & GPU Comparison | llmrun