Gemma 3 12B IT vs Qwen3.6 35B A3B

Qwen3.6 35B A3B leads llmrun Score 106.8 to 74.2; both fit 24 GB at Q4_K_M; Qwen3.6 35B A3B is 1.8× faster on RTX 4090 (~151 vs ~82 tok/s).

Model A · Google

Gemma 3 12B IT

74.2llmrun Score

12.2B · 32K context · Gemma Terms · Mar 2025

Vision

Model B · Alibaba

Qwen3.6 35B A3B

106.8llmrun Score

36.0B · 4.7B active · 256K context · Apache 2.0 · Apr 2026

VisionFunctions

Which should you choose?

Choose Gemma 3 12B IT if you want…

Fits a 12 GB GPU
Q4_K_M · 10.9 GB; Qwen3.6 35B A3B needs 10.4 GB at its smallest quant
Lighter on memory
8.0 vs 22.0 GB at Q4_K_M

Choose Qwen3.6 35B A3B if you want…

Higher llmrun Score
106.8 vs 74.2
Stronger at science
110.1 vs 71.6
Stronger at reasoning
103.7 vs 66.4
Ahead on the benchmarks
6 of 6 shared boards
1.8× faster on RTX 4090
~151 vs ~82 tok/s
Longer context window
256K vs 32K tokens

On your hardware

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

MemoryGemma 3 12B ITQwen3.6 35B A3B

8 GB

RTX 4060 · 8 GB tier

Gemma 3 12B IT

IQ2_M · ~39 tok/s

7.4 GB · up to 16Kfits

Qwen3.6 35B A3B

Doesn't fit

smallest quant needs 10.4 GB

12 GB

RTX 3060 12GB · 12 GB tier

Gemma 3 12B IT

Q4_K_M · ~29 tok/s

10.9 GB · up to 16Kmore headroom

Qwen3.6 35B A3B

IQ2_S · ~114 tok/s

11.7 GB · up to 32K

16 GB

RTX 5060 Ti 16GB · 16 GB tier

Gemma 3 12B IT

Q4_K_M · ~36 tok/s

10.9 GB · up to 32Kmore headroom

Qwen3.6 35B A3B

Q2_K · ~108 tok/s

15.7 GB · up to 32K

24 GBreference

RTX 4090 · 24 GB tier

Gemma 3 12B IT

Q4_K_M · ~82 tok/s

10.9 GB · up to 32K

Qwen3.6 35B A3B

Q4_K_M · ~151 tok/s

22 GB · up to 128Kfaster

32 GB

RTX 5090 · 32 GB tier

Gemma 3 12B IT

Q4_K_M · ~145 tok/s

10.9 GB · up to 32K

Qwen3.6 35B A3B

Q4_K_M · ~213 tok/s

22 GB · up to 256Kfaster

48 GB

RTX A6000 · 48 GB tier

Gemma 3 12B IT

Q4_K_M · ~62 tok/s

10.9 GB · up to 32K

Qwen3.6 35B A3B

Q4_K_M · ~125 tok/s

22 GB · up to 256Kfaster

Mac 32 GB

Mac Mini M4 · Macs

Gemma 3 12B IT

Q4_K_M · ~10 tok/s

10.9 GB · up to 32K

Qwen3.6 35B A3B

Q4_K_M · ~24 tok/s

22 GB · up to 256Kfaster

Mac 64 GB

Mac Studio M4 Max · Macs

Gemma 3 12B IT

Q4_K_M · ~48 tok/s

10.9 GB · up to 32K

Qwen3.6 35B A3B

Q4_K_M · ~64 tok/s

22 GB · up to 256Kfaster

Mac 128 GB

Mac Studio M4 Max · Macs

Gemma 3 12B IT

Q4_K_M · ~48 tok/s

10.9 GB · up to 32K

Qwen3.6 35B A3B

Q4_K_M · ~64 tok/s

22 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 3 12B IT Qwen3.6 35B A3B

Overall

Gemma 3 12B IT

74.269–80

Qwen3.6 35B A3B

106.8104–110

Coding

Gemma 3 12B IT

no data

Qwen3.6 35B A3B

105.399–112

Math

Gemma 3 12B IT

no data

Qwen3.6 35B A3B

109.0104–114

Science

Gemma 3 12B IT

71.660–83

Qwen3.6 35B A3B

110.1101–119

Reasoning

Gemma 3 12B IT

66.452–81

Qwen3.6 35B A3B

103.796–112

Gemma 3 12B IT · #96 of 106 open models · #28 of 36 that fit 24 GB

Qwen3.6 35B A3B · #41 of 106 open models · #3 of 36 that fit 24 GB

Benchmarks

6 shared boards: Gemma 3 12B IT leads 0, Qwen3.6 35B A3B leads 6 · Benchmarks imported Nov 2026

BoardGemma 3 12B ITQwen3.6 35B A3B

GPQA Diamond

Gemma 3 12B IT

39.5%#73/100 open

IndependentEpoch AI · Mar 2025

Qwen3.6 35B A3B

84.9%#23/100 open

IndependentEpoch AI · Apr 2026

AIME 2024/2025

Gemma 3 12B IT

16.7%#57/88 open

IndependentEpoch AI · Mar 2025

Qwen3.6 35B A3B

86.7%#22/88 open

IndependentEpoch AI · Apr 2026

SciCode

Gemma 3 12B IT

16.4%#70/72 open

Lab-reportedEpoch AI · Mar 2025

Qwen3.6 35B A3B

36.6%#48/72 open

Lab-reportedEpoch AI · Apr 2026

CritPt

Gemma 3 12B IT

0.0%#56/84 open

Lab-reportedEpoch AI · Mar 2025

Qwen3.6 35B A3B

0.3%#51/84 open

Lab-reportedEpoch AI · Apr 2026

DTBench

Gemma 3 12B IT

48.8%#64/70 open

Lab-reportedEpoch AI · Mar 2025

Qwen3.6 35B A3B

73.9%#32/70 open

Lab-reportedEpoch AI · Apr 2026

LMCA

Gemma 3 12B IT

4.5%#55/56 open

Lab-reportedEpoch AI · Mar 2025

Qwen3.6 35B A3B

29.7%#20/56 open

Lab-reportedEpoch AI · Apr 2026

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

Only Gemma 3 12B IT (2)

LMArena Text1341.7
MMLU-Pro60.6%

Only Qwen3.6 35B A3B (5)

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 3 12B ITQwen3.6 35B A3B

Q2_K

Gemma 3 12B IT

5.7 GB4.8 GB file

32K 11.9 GB · 128K —

Qwen3.6 35B A3B

15.7 GB13.5 GB file

32K 15.9 GB · 128K 16.9 GB

Q3_K_S

Gemma 3 12B IT

5.9 GB5.5 GB file

32K 12.1 GB · 128K —

Qwen3.6 35B A3B

16.1 GB15.4 GB file

32K 16.4 GB · 128K 17.4 GB

Q3_K_M

Gemma 3 12B IT

6.5 GB6.0 GB file

32K 12.7 GB · 128K —

Qwen3.6 35B A3B

17.9 GB16.6 GB file

32K 18.2 GB · 128K 19.2 GB

Q4_0

Gemma 3 12B IT

6.7 GB6.9 GB file

32K 12.9 GB · 128K —

Qwen3.6 35B A3B

18.4 GB19.8 GB file

32K 18.6 GB · 128K 19.6 GB

Q4_K_M

Gemma 3 12B IT

8.0 GB7.3 GB file

32K 14.2 GB · 128K —

Qwen3.6 35B A3B

22.0 GB22.1 GB file

32K 22.2 GB · 128K 23.2 GB

Q5_K_M

Gemma 3 12B IT

9.6 GB8.4 GB file

32K 15.7 GB · 128K —

Qwen3.6 35B A3B

26.0 GB26.5 GB file

32K 26.3 GB · 128K 27.3 GB

Q6_K

Gemma 3 12B IT

11.1 GB9.7 GB file

32K 17.3 GB · 128K —

Qwen3.6 35B A3B

30.0 GB29.3 GB file

32K 30.3 GB · 128K 31.3 GB

Q8_0

Gemma 3 12B IT

13.4 GB12.5 GB file

32K 19.6 GB · 128K —

Qwen3.6 35B A3B

36.3 GB36.9 GB file

32K 36.6 GB · 128K 37.6 GB

20 more quants

IQ2_XXS

Gemma 3 12B IT

3.7 GB3.6 GB file

32K 9.9 GB · 128K —

Qwen3.6 35B A3B

10.3 GB10.8 GB file

32K 10.5 GB · 128K 11.5 GB

IQ2_XS

Gemma 3 12B IT

4.0 GB3.8 GB file

32K 10.2 GB · 128K —

Qwen3.6 35B A3B

11.2 GB11.7 GB file

32K 11.4 GB · 128K 12.4 GB

IQ2_S

Gemma 3 12B IT

4.2 GB4.0 GB file

32K 10.4 GB · 128K —

Qwen3.6 35B A3B

11.6 GB11.9 GB file

32K 11.9 GB · 128K 12.9 GB

IQ2_M

Gemma 3 12B IT

4.5 GB4.4 GB file

32K 10.7 GB · 128K —

Qwen3.6 35B A3B

12.5 GB11.5 GB file

32K 12.8 GB · 128K 13.8 GB

IQ3_XXS

Gemma 3 12B IT

5.2 GB4.8 GB file

32K 11.4 GB · 128K —

Qwen3.6 35B A3B

14.3 GB13.2 GB file

32K 14.6 GB · 128K 15.6 GB

Q2_K_S

Gemma 3 12B IT

5.4 GB4.4 GB file

32K 11.6 GB · 128K —

Qwen3.6 35B A3B

14.8 GB12.2 GB file

32K 15.0 GB · 128K 16.0 GB

IQ3_XS

Gemma 3 12B IT

5.5 GB5.2 GB file

32K 11.7 GB · 128K —

Qwen3.6 35B A3B

15.2 GB17.1 GB file

32K 15.5 GB · 128K 16.5 GB

IQ3_S

Gemma 3 12B IT

5.7 GB5.2 GB file

32K 11.9 GB · 128K —

Qwen3.6 35B A3B

15.7 GB13.7 GB file

32K 15.9 GB · 128K 16.9 GB

IQ3_M

Gemma 3 12B IT

6.0 GB5.7 GB file

32K 12.2 GB · 128K —

Qwen3.6 35B A3B

16.6 GB17.8 GB file

32K 16.8 GB · 128K 17.8 GB

Q3_K_L

Gemma 3 12B IT

6.9 GB6.5 GB file

32K 13.1 GB · 128K —

Qwen3.6 35B A3B

18.8 GB17.8 GB file

32K 19.1 GB · 128K 20.1 GB

IQ4_XS

Gemma 3 12B IT

7.2 GB6.6 GB file

32K 13.4 GB · 128K —

Qwen3.6 35B A3B

19.7 GB17.7 GB file

32K 20.0 GB · 128K 21.0 GB

IQ4_NL

Gemma 3 12B IT

7.5 GB6.9 GB file

32K 13.7 GB · 128K —

Qwen3.6 35B A3B

20.6 GB18.0 GB file

32K 20.9 GB · 128K 21.9 GB

Q4_1

Gemma 3 12B IT

7.5 GB7.6 GB file

32K 13.7 GB · 128K —

Qwen3.6 35B A3B

20.6 GB22.9 GB file

32K 20.9 GB · 128K 21.9 GB

Q4_K_S

Gemma 3 12B IT

7.5 GB6.9 GB file

32K 13.7 GB · 128K —

Qwen3.6 35B A3B

20.6 GB20.9 GB file

32K 20.9 GB · 128K 21.9 GB

Q4_K_L

Gemma 3 12B IT

8.2 GB7.5 GB file

32K 14.4 GB · 128K —

Qwen3.6 35B A3B

22.4 GB22.7 GB file

32K 22.7 GB · 128K 23.7 GB

Q5_0

Gemma 3 12B IT

8.4 GB8.2 GB file

32K 14.6 GB · 128K —

Qwen3.6 35B A3B

22.9 GB24.1 GB file

32K 23.1 GB · 128K 24.1 GB

Q5_1

Gemma 3 12B IT

not listed

Qwen3.6 35B A3B

25.1 GB26.1 GB file

32K 25.4 GB · 128K 26.4 GB

Q5_K_S

Gemma 3 12B IT

9.2 GB8.2 GB file

32K 15.4 GB · 128K —

Qwen3.6 35B A3B

25.1 GB24.9 GB file

32K 25.4 GB · 128K 26.4 GB

Q5_K_L

Gemma 3 12B IT

9.7 GB8.7 GB file

32K 15.9 GB · 128K —

Qwen3.6 35B A3B

26.5 GB26.2 GB file

32K 26.7 GB · 128K 27.7 GB

BF16

Gemma 3 12B IT

26.8 GB23.5 GB file

32K 33.0 GB · 128K —

Qwen3.6 35B A3B

72.3 GB69.4 GB file

32K 72.5 GB · 128K 73.6 GB

How to run each

Gemma 3 12B IT

Ollama · Q4_K_M

$ollama run hf.co/unsloth/gemma-3-12b-it-GGUF:Q4_K_M

All ways to run Gemma 3 12B IT →

Qwen3.6 35B A3B

Ollama · Q4_K_M

$ollama run hf.co/unsloth/Qwen3.6-35B-A3B-GGUF:Q4_K_M

All ways to run Qwen3.6 35B A3B →

Specifications

Specifications of Gemma 3 12B IT and Qwen3.6 35B A3B
Spec	Gemma 3 12B IT	Qwen3.6 35B A3B
Publisher	Google	Alibaba
Parameters	12.2B	36.0B
Active parameters	—	4.7B per token
Architecture	—	Qwen3_5MoeForConditionalGeneration
Context	32K tokens	256K tokens
Modalities	Vision	Vision, Function-calling
License	Gemma Terms	Apache 2.0
Released	Mar 2025	Apr 2026

Frequently Asked Questions

Which is better, Gemma 3 12B IT or Qwen3.6 35B A3B?

Qwen3.6 35B A3B leads llmrun Score 106.8 to 74.2; both fit 24 GB at Q4_K_M; Qwen3.6 35B A3B is 1.8× faster on RTX 4090 (~151 vs ~82 tok/s). Choose Gemma 3 12B IT for fits a 12 GB GPU and lighter on memory; choose Qwen3.6 35B A3B for higher llmrun Score and stronger at science.

Which needs less VRAM, Gemma 3 12B IT or Qwen3.6 35B A3B?

At Q4_K_M, Gemma 3 12B IT requires 8.0 GB while Qwen3.6 35B A3B needs 22.0 GB, making Gemma 3 12B IT the easier model to run on your local setup.

Which is faster on RTX 4090?

Estimated decode speed on RTX 4090 is about 82 tok/s for Gemma 3 12B IT (Q4_K_M) and 151 tok/s for Qwen3.6 35B A3B (Q4_K_M), so Qwen3.6 35B A3B is faster. Estimates, ±20%.

Can I run Gemma 3 12B IT or Qwen3.6 35B A3B on a 16 GB GPU?

Gemma 3 12B IT fits at Q4_K_M; Qwen3.6 35B A3B fits at Q2_K.

Which has a longer context window, Gemma 3 12B IT or Qwen3.6 35B A3B?

Gemma 3 12B IT supports 32,768 tokens and Qwen3.6 35B A3B supports 262,144 tokens.