Gemma 4 31B IT vs Qwen3.5 27B

Gemma 4 31B IT leads llmrun Score 106.7 to 103.8 (ranges overlap); 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

Qwen3.5 27B

103.8llmrun Score

27.8B · 256K context · Apache 2.0 · Feb 2026

VisionFunctions

Which should you choose?

Choose Gemma 4 31B IT if you want…

Higher llmrun Score
106.7 vs 103.8, ranges overlap
Stronger at coding
107.1 vs 98.2
Ahead on the benchmarks
3 of 4 shared boards

Choose Qwen3.5 27B if you want…

Fits a 12 GB GPU
IQ3_XXS · 12 GB; Gemma 4 31B IT needs 11.5 GB at its smallest quant

On your hardware

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

MemoryGemma 4 31B ITQwen3.5 27B

8 GB

RTX 4060 · 8 GB tier

Gemma 4 31B IT

Doesn't fit

smallest quant needs 11.5 GB

Qwen3.5 27B

Doesn't fit

smallest quant needs 8.8 GB

12 GB

RTX 3060 12GB · 12 GB tier

Gemma 4 31B IT

IQ2_XXS · ~23 tok/s

11.5 GB · up to 16K

Qwen3.5 27B

IQ3_XXS · ~20 tok/s

12 GB · up to 16Kbetter quant

16 GB

RTX 5060 Ti 16GB · 16 GB tier

Gemma 4 31B IT

IQ3_XS · ~20 tok/s

15.8 GB · up to 16K

Qwen3.5 27B

Q3_K_L · ~19 tok/s

15.4 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

Qwen3.5 27B

Q4_K_M · ~38 tok/s

17.9 GB · up to 64Kfaster

32 GB

RTX 5090 · 32 GB tier

Gemma 4 31B IT

Q4_K_M · ~57 tok/s

21.7 GB · up to 64K

Qwen3.5 27B

Q4_K_M · ~67 tok/s

17.9 GB · up to 256Kfaster

48 GB

RTX A6000 · 48 GB tier

Gemma 4 31B IT

Q4_K_M · ~25 tok/s

21.7 GB · up to 128K

Qwen3.5 27B

Q4_K_M · ~29 tok/s

17.9 GB · up to 256Kfaster

Mac 32 GB

Mac Mini M4 · Macs

Gemma 4 31B IT

Q4_K_M · ~4 tok/s

21.7 GB · up to 64K

Qwen3.5 27B

Q4_K_M · ~5 tok/s

17.9 GB · up to 128Kfaster

Mac 64 GB

Mac Studio M4 Max · Macs

Gemma 4 31B IT

Q4_K_M · ~19 tok/s

21.7 GB · up to 256K

Qwen3.5 27B

Q4_K_M · ~22 tok/s

17.9 GB · up to 256Kfaster

Mac 128 GB

Mac Studio M4 Max · Macs

Gemma 4 31B IT

Q4_K_M · ~19 tok/s

21.7 GB · up to 256K

Qwen3.5 27B

Q4_K_M · ~22 tok/s

17.9 GB · up to 256Kfaster

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

Gemma 4 31B IT Qwen3.5 27B

Overall

Gemma 4 31B IT

106.7104–110

Qwen3.5 27B

103.898–110

Coding

Gemma 4 31B IT

107.1103–112

Qwen3.5 27B

98.288–108

Science

Gemma 4 31B IT

105.297–114

Qwen3.5 27B

no data

Reasoning

Gemma 4 31B IT

111.1104–119

Qwen3.5 27B

110.5101–120

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

Qwen3.5 27B · #48 of 106 open models · #7 of 36 that fit 24 GB

Benchmarks

4 shared boards: Gemma 4 31B IT leads 3, Qwen3.5 27B leads 0 · Benchmarks imported Nov 2026

BoardGemma 4 31B ITQwen3.5 27B

WeirdML

Gemma 4 31B IT

52.3%#9/47 open

IndependentEpoch AI · Apr 2026

Qwen3.5 27B

39.5%#24/47 open

IndependentEpoch AI · Feb 2026

ALE-Bench

Gemma 4 31B IT

925.5#17/48 open

Lab-reportedEpoch AI · Apr 2026

Qwen3.5 27B

349.4#41/48 open

Lab-reportedEpoch AI · Feb 2026

DTBench

Gemma 4 31B IT

82.7%#20/70 open

Lab-reportedEpoch AI · Apr 2026

Qwen3.5 27B

82.4%#21/70 open

Lab-reportedEpoch AI · Feb 2026

LMCA

Gemma 4 31B IT

39.3%#9/56 open

Lab-reportedEpoch AI · Apr 2026

Qwen3.5 27B

34.0%#17/56 open

Lab-reportedEpoch AI · Feb 2026

18 more boards (other shared and single-model boards)

LMArena Text

Gemma 4 31B IT

1452.3#14/188 open

ArenaLMArena · Oct 2026

Qwen3.5 27B

1408.8#45/188 open

ArenaLMArena · Oct 2026

LMArena WebDev

Gemma 4 31B IT

1368.7#35/55 open

ArenaLMArena · Oct 2026

Qwen3.5 27B

1358.3#39/55 open

ArenaLMArena · Oct 2026

Only Gemma 4 31B IT (14)

Only Qwen3.5 27B (2)

MMLU-Pro86.1%
Vending-Bench 2202.0

VRAM by quantization

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

QuantGemma 4 31B ITQwen3.5 27B

Q2_K

Gemma 4 31B IT

14.9 GB12.6 GB file

32K 18.4 GB · 128K 31.0 GB

Qwen3.5 27B

12.6 GB12.1 GB file

32K 13.9 GB · 128K 19.3 GB

Q3_K_S

Gemma 4 31B IT

15.3 GB13.2 GB file

32K 18.7 GB · 128K 31.4 GB

Qwen3.5 27B

12.9 GB12.3 GB file

32K 14.2 GB · 128K 19.6 GB

Q3_K_M

Gemma 4 31B IT

16.9 GB14.7 GB file

32K 20.3 GB · 128K 33.0 GB

Qwen3.5 27B

14.3 GB13.5 GB file

32K 15.6 GB · 128K 21.0 GB

Q4_0

Gemma 4 31B IT

17.3 GB17.3 GB file

32K 20.7 GB · 128K 33.4 GB

Qwen3.5 27B

14.6 GB15.7 GB file

32K 16.0 GB · 128K 21.4 GB

Q4_K_M

Gemma 4 31B IT

20.4 GB18.3 GB file

32K 23.8 GB · 128K 36.5 GB

Qwen3.5 27B

17.4 GB16.7 GB file

32K 18.8 GB · 128K 24.1 GB

Q5_K_M

Gemma 4 31B IT

23.9 GB21.7 GB file

32K 27.3 GB · 128K 40.0 GB

Qwen3.5 27B

20.5 GB19.6 GB file

32K 21.9 GB · 128K 27.3 GB

Q6_K

Gemma 4 31B IT

27.4 GB25.2 GB file

32K 30.9 GB · 128K 43.5 GB

Qwen3.5 27B

23.7 GB22.5 GB file

32K 25.0 GB · 128K 30.4 GB

Q8_0

Gemma 4 31B IT

32.9 GB32.6 GB file

32K 36.3 GB · 128K 49.0 GB

Qwen3.5 27B

28.5 GB28.6 GB file

32K 29.9 GB · 128K 35.2 GB

20 more quants

IQ2_XXS

Gemma 4 31B IT

10.2 GB8.5 GB file

32K 13.7 GB · 128K 26.3 GB

Qwen3.5 27B

8.4 GB8.6 GB file

32K 9.7 GB · 128K 15.1 GB

IQ2_XS

Gemma 4 31B IT

11.0 GB11.5 GB file

32K 14.4 GB · 128K 27.1 GB

Qwen3.5 27B

9.1 GB10.2 GB file

32K 10.4 GB · 128K 15.8 GB

IQ2_S

Gemma 4 31B IT

11.4 GB12.1 GB file

32K 14.8 GB · 128K 27.5 GB

Qwen3.5 27B

9.4 GB10.5 GB file

32K 10.8 GB · 128K 16.1 GB

IQ2_M

Gemma 4 31B IT

12.2 GB10.8 GB file

32K 15.6 GB · 128K 28.3 GB

Qwen3.5 27B

10.1 GB10.2 GB file

32K 11.5 GB · 128K 16.8 GB

IQ3_XXS

Gemma 4 31B IT

13.7 GB11.8 GB file

32K 17.2 GB · 128K 29.9 GB

Qwen3.5 27B

11.5 GB11.5 GB file

32K 12.9 GB · 128K 18.2 GB

Q2_K_S

Gemma 4 31B IT

14.1 GB11.0 GB file

32K 17.6 GB · 128K 30.3 GB

Qwen3.5 27B

11.9 GB9.7 GB file

32K 13.2 GB · 128K 18.6 GB

IQ3_XS

Gemma 4 31B IT

14.5 GB13.8 GB file

32K 18.0 GB · 128K 30.6 GB

Qwen3.5 27B

12.2 GB13.5 GB file

32K 13.6 GB · 128K 18.9 GB

IQ3_S

Gemma 4 31B IT

14.9 GB13.8 GB file

32K 18.4 GB · 128K 31.0 GB

Qwen3.5 27B

12.6 GB12.1 GB file

32K 13.9 GB · 128K 19.3 GB

IQ3_M

Gemma 4 31B IT

15.7 GB15.1 GB file

32K 19.1 GB · 128K 31.8 GB

Qwen3.5 27B

13.3 GB14.1 GB file

32K 14.6 GB · 128K 20.0 GB

Q3_K_L

Gemma 4 31B IT

17.7 GB16.8 GB file

32K 21.1 GB · 128K 33.8 GB

Qwen3.5 27B

15.0 GB15.5 GB file

32K 16.3 GB · 128K 21.7 GB

IQ4_XS

Gemma 4 31B IT

18.4 GB16.4 GB file

32K 21.9 GB · 128K 34.6 GB

Qwen3.5 27B

15.7 GB15.0 GB file

32K 17.0 GB · 128K 22.4 GB

IQ4_NL

Gemma 4 31B IT

19.2 GB17.3 GB file

32K 22.7 GB · 128K 35.3 GB

Qwen3.5 27B

16.4 GB15.7 GB file

32K 17.7 GB · 128K 23.1 GB

Q4_1

Gemma 4 31B IT

19.2 GB19.1 GB file

32K 22.7 GB · 128K 35.3 GB

Qwen3.5 27B

16.4 GB17.2 GB file

32K 17.7 GB · 128K 23.1 GB

Q4_K_S

Gemma 4 31B IT

19.2 GB17.4 GB file

32K 22.7 GB · 128K 35.3 GB

Qwen3.5 27B

16.4 GB15.8 GB file

32K 17.7 GB · 128K 23.1 GB

Q4_K_L

Gemma 4 31B IT

20.8 GB19.9 GB file

32K 24.2 GB · 128K 36.9 GB

Qwen3.5 27B

17.8 GB18.9 GB file

32K 19.1 GB · 128K 24.5 GB

Q5_0

Gemma 4 31B IT

21.2 GB21.3 GB file

32K 24.6 GB · 128K 37.3 GB

Qwen3.5 27B

18.1 GB18.7 GB file

32K 19.5 GB · 128K 24.8 GB

Q5_1

Gemma 4 31B IT

not listed

Qwen3.5 27B

19.9 GB20.3 GB file

32K 21.2 GB · 128K 26.6 GB

Q5_K_S

Gemma 4 31B IT

23.1 GB21.1 GB file

32K 26.6 GB · 128K 39.2 GB

Qwen3.5 27B

19.9 GB18.9 GB file

32K 21.2 GB · 128K 26.6 GB

Q5_K_L

Gemma 4 31B IT

24.3 GB23.0 GB file

32K 27.7 GB · 128K 40.4 GB

Qwen3.5 27B

20.9 GB21.7 GB file

32K 22.2 GB · 128K 27.6 GB

BF16

Gemma 4 31B IT

64.2 GB61.4 GB file

32K 67.6 GB · 128K 80.3 GB

Qwen3.5 27B

56.3 GB53.8 GB file

32K 57.7 GB · 128K 63.0 GB

How to run each

Gemma 4 31B IT

Ollama · Q4_K_M

$ollama run hf.co/unsloth/gemma-4-31B-it-GGUF:Q4_K_M

All ways to run Gemma 4 31B IT →

Qwen3.5 27B

Ollama · Q4_K_M

$ollama run hf.co/unsloth/Qwen3.5-27B-GGUF:Q4_K_M

All ways to run Qwen3.5 27B →

Specifications

Specifications of Gemma 4 31B IT and Qwen3.5 27B
Spec	Gemma 4 31B IT	Qwen3.5 27B
Publisher	Google	Alibaba
Parameters	31.3B	27.8B
Architecture	Gemma4ForConditionalGeneration	Qwen3_5ForConditionalGeneration
Context	256K tokens	256K tokens
Modalities	Vision, Function-calling	Vision, Function-calling
License	Apache 2.0	Apache 2.0
Released	Mar 2026	Feb 2026

Frequently Asked Questions

Which is better, Gemma 4 31B IT or Qwen3.5 27B?

Gemma 4 31B IT leads llmrun Score 106.7 to 103.8 (ranges overlap); both fit 24 GB at Q4_K_M. Choose Gemma 4 31B IT for higher llmrun Score and stronger at coding; choose Qwen3.5 27B for fits a 12 GB GPU.

Which needs less VRAM, Gemma 4 31B IT or Qwen3.5 27B?

At Q4_K_M, Gemma 4 31B IT requires 20.4 GB while Qwen3.5 27B needs 17.4 GB, making Qwen3.5 27B 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 38 tok/s for Qwen3.5 27B (Q4_K_M), so Qwen3.5 27B is faster. Estimates, ±20%.

Can I run Gemma 4 31B IT or Qwen3.5 27B on a 16 GB GPU?

Gemma 4 31B IT fits at IQ3_XS; Qwen3.5 27B fits at Q3_K_L.

Which has a longer context window, Gemma 4 31B IT or Qwen3.5 27B?

Gemma 4 31B IT supports 262,144 tokens and Qwen3.5 27B supports 262,144 tokens.