llmrun

Gemma 4 31B IT vs Qwen3 32B

Gemma 4 31B IT leads llmrun Score 106.7 to 98.6; both fit 24 GB at Q4_K_M.

Model A · Google

Gemma 4 31B IT
106.7llmrun Score

31.3B · 256K context · Apache 2.0 · Mar 2026

VisionFunctions

Model B · Alibaba

Qwen3 32B
98.6llmrun Score

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

ChatFunctions

Which should you choose?

Choose Gemma 4 31B IT if you want…

  • Higher llmrun Score

    106.7 vs 98.6

  • Stronger at reasoning

    111.1 vs 91.5

  • Stronger at coding

    107.1 vs 93.2

  • Ahead on the benchmarks

    6 of 6 shared boards

  • Longer context window

    256K vs 40K tokens

  • Also does vision

    Qwen3 32B doesn't list it

Choose Qwen3 32B if you want…

  • Also does chat

    Gemma 4 31B IT 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

Gemma 4 31B IT

Doesn't fit

smallest quant needs 11.5 GB

Qwen3 32B

Doesn't fit

smallest quant needs 12 GB

12 GB

RTX 3060 12GB · 12 GB tier

Gemma 4 31B IT

IQ2_XXS · ~23 tok/s

11.5 GB · up to 16K

Qwen3 32B

IQ2_XXS · ~24 tok/s

12 GB · up to 16K

16 GB

RTX 5060 Ti 16GB · 16 GB tier

Gemma 4 31B IT

IQ3_XS · ~20 tok/s

15.8 GB · up to 16K

Qwen3 32B

IQ3_XXS · ~22 tok/s

15.7 GB · up to 16K

24 GBreference

RTX 4090 · 24 GB tier

Gemma 4 31B IT

Q4_K_M · ~32 tok/s

21.7 GB · up to 32K

Qwen3 32B

Q4_K_M · ~32 tok/s

22.6 GB · up to 16K

32 GB

RTX 5090 · 32 GB tier

Gemma 4 31B IT

Q4_K_M · ~57 tok/s

21.7 GB · up to 64K

Qwen3 32B

Q4_K_M · ~57 tok/s

22.6 GB · up to 40K

48 GB

RTX A6000 · 48 GB tier

Gemma 4 31B IT

Q4_K_M · ~25 tok/s

21.7 GB · up to 128K

Qwen3 32B

Q4_K_M · ~25 tok/s

22.6 GB · up to 40K

Mac 32 GB

Mac Mini M4 · Macs

Gemma 4 31B IT

Q4_K_M · ~4 tok/s

21.7 GB · up to 64K

Qwen3 32B

Q4_K_M · ~4 tok/s

22.6 GB · up to 40K

Mac 64 GB

Mac Studio M4 Max · Macs

Gemma 4 31B IT

Q4_K_M · ~19 tok/s

21.7 GB · up to 256K

Qwen3 32B

Q4_K_M · ~19 tok/s

22.6 GB · up to 40K

Mac 128 GB

Mac Studio M4 Max · Macs

Gemma 4 31B IT

Q4_K_M · ~19 tok/s

21.7 GB · up to 256K

Qwen3 32B

Q4_K_M · ~19 tok/s

22.6 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

Gemma 4 31B IT

106.7104–110

Qwen3 32B

98.696–102

Coding

Gemma 4 31B IT

107.1103–112

Qwen3 32B

93.287–99

Science

Gemma 4 31B IT

105.297–114

Qwen3 32B

96.089–104

Reasoning

Gemma 4 31B IT

111.1104–119

Qwen3 32B

91.583–100

Gemma 4 31B IT · #42 of 106 open models · #4 of 36 that fit 24 GB

Qwen3 32B · #62 of 106 open models · #11 of 36 that fit 24 GB

Benchmarks

6 shared boards: Gemma 4 31B IT leads 6, Qwen3 32B leads 0 · Benchmarks imported Nov 2026

GPQA Diamond

Gemma 4 31B IT

75.8%#30/100 open

IndependentEpoch AI · Apr 2026

Qwen3 32B

65.7%#39/100 open

IndependentEpoch AI · Apr 2025

AIME 2024/2025

Gemma 4 31B IT

73.3%#28/88 open

IndependentEpoch AI · Apr 2026

Qwen3 32B

66.9%#33/88 open

IndependentEpoch AI · Apr 2025

SciCode

Gemma 4 31B IT

45.5%#25/72 open

Lab-reportedEpoch AI · Apr 2026

Qwen3 32B

35.4%#54/72 open

Lab-reportedEpoch AI · Apr 2025

CritPt

Gemma 4 31B IT

1.4%#35/84 open

Lab-reportedEpoch AI · Apr 2026

Qwen3 32B

0.3%#50/84 open

Lab-reportedEpoch AI · Apr 2025

DTBench

Gemma 4 31B IT

82.7%#20/70 open

Lab-reportedEpoch AI · Apr 2026

Qwen3 32B

67.5%#37/70 open

Lab-reportedEpoch AI · Apr 2025

LMCA

Gemma 4 31B IT

39.3%#9/56 open

Lab-reportedEpoch AI · Apr 2026

Qwen3 32B

17.3%#39/56 open

Lab-reportedEpoch AI · Apr 2025

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

Gemma 4 31B IT

1452.3#14/188 open

ArenaLMArena · Oct 2026

Qwen3 32B

1346.8#80/188 open

ArenaLMArena · Oct 2026

Only Qwen3 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

Gemma 4 31B IT

14.9 GB12.6 GB file

32K 18.4 GB · 128K 31.0 GB

Qwen3 32B

14.6 GB12.3 GB file

32K 19.6 GB · 128K —

Q3_K_S

Gemma 4 31B IT

15.3 GB13.2 GB file

32K 18.7 GB · 128K 31.4 GB

Qwen3 32B

15.0 GB14.4 GB file

32K 20.0 GB · 128K —

Q3_K_M

Gemma 4 31B IT

16.9 GB14.7 GB file

32K 20.3 GB · 128K 33.0 GB

Qwen3 32B

16.6 GB16.0 GB file

32K 21.6 GB · 128K —

Q4_0

Gemma 4 31B IT

17.3 GB17.3 GB file

32K 20.7 GB · 128K 33.4 GB

Qwen3 32B

17.0 GB18.7 GB file

32K 22.1 GB · 128K —

Q4_K_M

Gemma 4 31B IT

20.4 GB18.3 GB file

32K 23.8 GB · 128K 36.5 GB

Qwen3 32B

20.3 GB19.8 GB file

32K 25.3 GB · 128K —

Q5_K_M

Gemma 4 31B IT

23.9 GB21.7 GB file

32K 27.3 GB · 128K 40.0 GB

Qwen3 32B

24.0 GB23.2 GB file

32K 29.0 GB · 128K —

Q6_K

Gemma 4 31B IT

27.4 GB25.2 GB file

32K 30.9 GB · 128K 43.5 GB

Qwen3 32B

27.7 GB26.9 GB file

32K 32.7 GB · 128K —

Q8_0

Gemma 4 31B IT

32.9 GB32.6 GB file

32K 36.3 GB · 128K 49.0 GB

Qwen3 32B

33.4 GB34.8 GB file

32K 38.4 GB · 128K —

19 more quants

IQ2_XXS

Gemma 4 31B IT

10.2 GB8.5 GB file

32K 13.7 GB · 128K 26.3 GB

Qwen3 32B

9.7 GB9.3 GB file

32K 14.7 GB · 128K —

IQ2_XS

Gemma 4 31B IT

11.0 GB11.5 GB file

32K 14.4 GB · 128K 27.1 GB

Qwen3 32B

10.5 GB10.0 GB file

32K 15.5 GB · 128K —

IQ2_S

Gemma 4 31B IT

11.4 GB12.1 GB file

32K 14.8 GB · 128K 27.5 GB

Qwen3 32B

10.9 GB10.5 GB file

32K 15.9 GB · 128K —

IQ2_M

Gemma 4 31B IT

12.2 GB10.8 GB file

32K 15.6 GB · 128K 28.3 GB

Qwen3 32B

11.7 GB11.6 GB file

32K 16.7 GB · 128K —

IQ3_XXS

Gemma 4 31B IT

13.7 GB11.8 GB file

32K 17.2 GB · 128K 29.9 GB

Qwen3 32B

13.3 GB13.0 GB file

32K 18.4 GB · 128K —

Q2_K_S

Gemma 4 31B IT

14.1 GB11.0 GB file

32K 17.6 GB · 128K 30.3 GB

Qwen3 32B

13.7 GB11.5 GB file

32K 18.8 GB · 128K —

IQ3_XS

Gemma 4 31B IT

14.5 GB13.8 GB file

32K 18.0 GB · 128K 30.6 GB

Qwen3 32B

14.2 GB13.7 GB file

32K 19.2 GB · 128K —

IQ3_S

Gemma 4 31B IT

14.9 GB13.8 GB file

32K 18.4 GB · 128K 31.0 GB

Qwen3 32B

14.6 GB14.4 GB file

32K 19.6 GB · 128K —

IQ3_M

Gemma 4 31B IT

15.7 GB15.1 GB file

32K 19.1 GB · 128K 31.8 GB

Qwen3 32B

15.4 GB14.9 GB file

32K 20.4 GB · 128K —

Q3_K_L

Gemma 4 31B IT

17.7 GB16.8 GB file

32K 21.1 GB · 128K 33.8 GB

Qwen3 32B

17.4 GB17.3 GB file

32K 22.5 GB · 128K —

IQ4_XS

Gemma 4 31B IT

18.4 GB16.4 GB file

32K 21.9 GB · 128K 34.6 GB

Qwen3 32B

18.3 GB17.7 GB file

32K 23.3 GB · 128K —

IQ4_NL

Gemma 4 31B IT

19.2 GB17.3 GB file

32K 22.7 GB · 128K 35.3 GB

Qwen3 32B

19.1 GB18.7 GB file

32K 24.1 GB · 128K —

Q4_1

Gemma 4 31B IT

19.2 GB19.1 GB file

32K 22.7 GB · 128K 35.3 GB

Qwen3 32B

19.1 GB20.6 GB file

32K 24.1 GB · 128K —

Q4_K_S

Gemma 4 31B IT

19.2 GB17.4 GB file

32K 22.7 GB · 128K 35.3 GB

Qwen3 32B

19.1 GB18.8 GB file

32K 24.1 GB · 128K —

Q4_K_L

Gemma 4 31B IT

20.8 GB19.9 GB file

32K 24.2 GB · 128K 36.9 GB

Qwen3 32B

20.7 GB20.3 GB file

32K 25.7 GB · 128K —

Q5_0

Gemma 4 31B IT

21.2 GB21.3 GB file

32K 24.6 GB · 128K 37.3 GB

Qwen3 32B

21.1 GB22.6 GB file

32K 26.1 GB · 128K —

Q5_K_S

Gemma 4 31B IT

23.1 GB21.1 GB file

32K 26.6 GB · 128K 39.2 GB

Qwen3 32B

23.2 GB22.6 GB file

32K 28.2 GB · 128K —

Q5_K_L

Gemma 4 31B IT

24.3 GB23.0 GB file

32K 27.7 GB · 128K 40.4 GB

Qwen3 32B

24.4 GB23.7 GB file

32K 29.4 GB · 128K —

BF16

Gemma 4 31B IT

64.2 GB61.4 GB file

32K 67.6 GB · 128K 80.3 GB

Qwen3 32B

66.2 GB65.5 GB file

32K 71.2 GB · 128K —

How to run each

Specifications

Specifications of Gemma 4 31B IT and Qwen3 32B
SpecGemma 4 31B ITQwen3 32B
PublisherGoogleAlibaba
Parameters31.3B32.8B
ArchitectureGemma4ForConditionalGenerationQwen3ForCausalLM
Context256K tokens40K tokens
ModalitiesVision, Function-callingChat, Function-calling
LicenseApache 2.0Apache 2.0
ReleasedMar 2026Apr 2025

Frequently Asked Questions

Which is better, Gemma 4 31B IT or Qwen3 32B?

Gemma 4 31B IT leads llmrun Score 106.7 to 98.6; both fit 24 GB at Q4_K_M. Choose Gemma 4 31B IT for higher llmrun Score and stronger at reasoning; choose Qwen3 32B for also does chat.

Which needs less VRAM, Gemma 4 31B IT or Qwen3 32B?

At Q4_K_M, Gemma 4 31B IT requires 20.4 GB while Qwen3 32B needs 20.3 GB, making Qwen3 32B the easier model to run on your local setup.

Which is faster on RTX 4090?

Estimated decode speed on RTX 4090 is about 32 tok/s for Gemma 4 31B IT (Q4_K_M) and 32 tok/s for Qwen3 32B (Q4_K_M), so Gemma 4 31B IT is faster. Estimates, ±20%.

Can I run Gemma 4 31B IT or Qwen3 32B on a 16 GB GPU?

Gemma 4 31B IT fits at IQ3_XS; Qwen3 32B fits at IQ3_XXS.

Which has a longer context window, Gemma 4 31B IT or Qwen3 32B?

Gemma 4 31B IT supports 262,144 tokens and Qwen3 32B supports 40,960 tokens.

Gemma 4 31B IT vs Qwen3 32B — VRAM & GPU Comparison | llmrun