Qwen3 32B vs Qwen3.6 35B A3B

Qwen3.6 35B A3B leads llmrun Score 106.8 to 98.6; both fit 24 GB at Q4_K_M; Qwen3.6 35B A3B is 4.7× faster on RTX 4090 (~151 vs ~32 tok/s).

Model A · Alibaba

Qwen3 32B

98.6llmrun Score

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

ChatFunctions

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 Qwen3 32B if you want…

Fits a 16 GB GPU
IQ3_XXS · 15.7 GB; Qwen3.6 35B A3B needs 10.4 GB at its smallest quant
Also does chat
Qwen3.6 35B A3B doesn't list it

Choose Qwen3.6 35B A3B if you want…

Higher llmrun Score
106.8 vs 98.6
Stronger at science
110.1 vs 96.0
Stronger at reasoning
103.7 vs 91.5
Ahead on the benchmarks
5 of 6 shared boards
4.7× faster on RTX 4090
~151 vs ~32 tok/s
Longer context window
256K vs 40K tokens

On your hardware

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

MemoryQwen3 32BQwen3.6 35B A3B

8 GB

RTX 4060 · 8 GB tier

Qwen3 32B

Doesn't fit

smallest quant needs 12 GB

Qwen3.6 35B A3B

Doesn't fit

smallest quant needs 10.4 GB

12 GB

RTX 3060 12GB · 12 GB tier

Qwen3 32B

IQ2_XXS · ~24 tok/s

12 GB · up to 16K

Qwen3.6 35B A3B

IQ2_S · ~114 tok/s

11.7 GB · up to 32K

16 GB

RTX 5060 Ti 16GB · 16 GB tier

Qwen3 32B

IQ3_XXS · ~22 tok/s

15.7 GB · up to 16Kbetter quant

Qwen3.6 35B A3B

Q2_K · ~108 tok/s

15.7 GB · up to 32K

24 GBreference

RTX 4090 · 24 GB tier

Qwen3 32B

Q4_K_M · ~32 tok/s

22.6 GB · up to 16K

Qwen3.6 35B A3B

Q4_K_M · ~151 tok/s

22 GB · up to 128Kfaster

32 GB

RTX 5090 · 32 GB tier

Qwen3 32B

Q4_K_M · ~57 tok/s

22.6 GB · up to 40K

Qwen3.6 35B A3B

Q4_K_M · ~213 tok/s

22 GB · up to 256Kfaster

48 GB

RTX A6000 · 48 GB tier

Qwen3 32B

Q4_K_M · ~25 tok/s

22.6 GB · up to 40K

Qwen3.6 35B A3B

Q4_K_M · ~125 tok/s

22 GB · up to 256Kfaster

Mac 32 GB

Mac Mini M4 · Macs

Qwen3 32B

Q4_K_M · ~4 tok/s

22.6 GB · up to 40K

Qwen3.6 35B A3B

Q4_K_M · ~24 tok/s

22 GB · up to 256Kfaster

Mac 64 GB

Mac Studio M4 Max · Macs

Qwen3 32B

Q4_K_M · ~19 tok/s

22.6 GB · up to 40K

Qwen3.6 35B A3B

Q4_K_M · ~64 tok/s

22 GB · up to 256Kfaster

Mac 128 GB

Mac Studio M4 Max · Macs

Qwen3 32B

Q4_K_M · ~19 tok/s

22.6 GB · up to 40K

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

Qwen3 32B Qwen3.6 35B A3B

Overall

Qwen3 32B

98.696–102

Qwen3.6 35B A3B

106.8104–110

Coding

Qwen3 32B

93.287–99

Qwen3.6 35B A3B

105.399–112

Math

Qwen3 32B

no data

Qwen3.6 35B A3B

109.0104–114

Science

Qwen3 32B

96.089–104

Qwen3.6 35B A3B

110.1101–119

Reasoning

Qwen3 32B

91.583–100

Qwen3.6 35B A3B

103.796–112

Qwen3 32B · #62 of 106 open models · #11 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: Qwen3 32B leads 0, Qwen3.6 35B A3B leads 5 · Benchmarks imported Nov 2026

BoardQwen3 32BQwen3.6 35B A3B

GPQA Diamond

Qwen3 32B

65.7%#39/100 open

IndependentEpoch AI · Apr 2025

Qwen3.6 35B A3B

84.9%#23/100 open

IndependentEpoch AI · Apr 2026

AIME 2024/2025

Qwen3 32B

66.9%#33/88 open

IndependentEpoch AI · Apr 2025

Qwen3.6 35B A3B

86.7%#22/88 open

IndependentEpoch AI · Apr 2026

SciCode

Qwen3 32B

35.4%#54/72 open

Lab-reportedEpoch AI · Apr 2025

Qwen3.6 35B A3B

36.6%#48/72 open

Lab-reportedEpoch AI · Apr 2026

CritPt

Qwen3 32B

0.3%#50/84 open

Lab-reportedEpoch AI · Apr 2025

Qwen3.6 35B A3B

0.3%#51/84 open

Lab-reportedEpoch AI · Apr 2026

DTBench

Qwen3 32B

67.5%#37/70 open

Lab-reportedEpoch AI · Apr 2025

Qwen3.6 35B A3B

73.9%#32/70 open

Lab-reportedEpoch AI · Apr 2026

LMCA

Qwen3 32B

17.3%#39/56 open

Lab-reportedEpoch AI · Apr 2025

Qwen3.6 35B A3B

29.7%#20/56 open

Lab-reportedEpoch AI · Apr 2026

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

Only Qwen3 32B (3)

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.

QuantQwen3 32BQwen3.6 35B A3B

Q2_K

Qwen3 32B

14.6 GB12.3 GB file

32K 19.6 GB · 128K —

Qwen3.6 35B A3B

15.7 GB13.5 GB file

32K 15.9 GB · 128K 16.9 GB

Q3_K_S

Qwen3 32B

15.0 GB14.4 GB file

32K 20.0 GB · 128K —

Qwen3.6 35B A3B

16.1 GB15.4 GB file

32K 16.4 GB · 128K 17.4 GB

Q3_K_M

Qwen3 32B

16.6 GB16.0 GB file

32K 21.6 GB · 128K —

Qwen3.6 35B A3B

17.9 GB16.6 GB file

32K 18.2 GB · 128K 19.2 GB

Q4_0

Qwen3 32B

17.0 GB18.7 GB file

32K 22.1 GB · 128K —

Qwen3.6 35B A3B

18.4 GB19.8 GB file

32K 18.6 GB · 128K 19.6 GB

Q4_K_M

Qwen3 32B

20.3 GB19.8 GB file

32K 25.3 GB · 128K —

Qwen3.6 35B A3B

22.0 GB22.1 GB file

32K 22.2 GB · 128K 23.2 GB

Q5_K_M

Qwen3 32B

24.0 GB23.2 GB file

32K 29.0 GB · 128K —

Qwen3.6 35B A3B

26.0 GB26.5 GB file

32K 26.3 GB · 128K 27.3 GB

Q6_K

Qwen3 32B

27.7 GB26.9 GB file

32K 32.7 GB · 128K —

Qwen3.6 35B A3B

30.0 GB29.3 GB file

32K 30.3 GB · 128K 31.3 GB

Q8_0

Qwen3 32B

33.4 GB34.8 GB file

32K 38.4 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

Qwen3 32B

9.7 GB9.3 GB file

32K 14.7 GB · 128K —

Qwen3.6 35B A3B

10.3 GB10.8 GB file

32K 10.5 GB · 128K 11.5 GB

IQ2_XS

Qwen3 32B

10.5 GB10.0 GB file

32K 15.5 GB · 128K —

Qwen3.6 35B A3B

11.2 GB11.7 GB file

32K 11.4 GB · 128K 12.4 GB

IQ2_S

Qwen3 32B

10.9 GB10.5 GB file

32K 15.9 GB · 128K —

Qwen3.6 35B A3B

11.6 GB11.9 GB file

32K 11.9 GB · 128K 12.9 GB

IQ2_M

Qwen3 32B

11.7 GB11.6 GB file

32K 16.7 GB · 128K —

Qwen3.6 35B A3B

12.5 GB11.5 GB file

32K 12.8 GB · 128K 13.8 GB

IQ3_XXS

Qwen3 32B

13.3 GB13.0 GB file

32K 18.4 GB · 128K —

Qwen3.6 35B A3B

14.3 GB13.2 GB file

32K 14.6 GB · 128K 15.6 GB

Q2_K_S

Qwen3 32B

13.7 GB11.5 GB file

32K 18.8 GB · 128K —

Qwen3.6 35B A3B

14.8 GB12.2 GB file

32K 15.0 GB · 128K 16.0 GB

IQ3_XS

Qwen3 32B

14.2 GB13.7 GB file

32K 19.2 GB · 128K —

Qwen3.6 35B A3B

15.2 GB17.1 GB file

32K 15.5 GB · 128K 16.5 GB

IQ3_S

Qwen3 32B

14.6 GB14.4 GB file

32K 19.6 GB · 128K —

Qwen3.6 35B A3B

15.7 GB13.7 GB file

32K 15.9 GB · 128K 16.9 GB

IQ3_M

Qwen3 32B

15.4 GB14.9 GB file

32K 20.4 GB · 128K —

Qwen3.6 35B A3B

16.6 GB17.8 GB file

32K 16.8 GB · 128K 17.8 GB

Q3_K_L

Qwen3 32B

17.4 GB17.3 GB file

32K 22.5 GB · 128K —

Qwen3.6 35B A3B

18.8 GB17.8 GB file

32K 19.1 GB · 128K 20.1 GB

IQ4_XS

Qwen3 32B

18.3 GB17.7 GB file

32K 23.3 GB · 128K —

Qwen3.6 35B A3B

19.7 GB17.7 GB file

32K 20.0 GB · 128K 21.0 GB

IQ4_NL

Qwen3 32B

19.1 GB18.7 GB file

32K 24.1 GB · 128K —

Qwen3.6 35B A3B

20.6 GB18.0 GB file

32K 20.9 GB · 128K 21.9 GB

Q4_1

Qwen3 32B

19.1 GB20.6 GB file

32K 24.1 GB · 128K —

Qwen3.6 35B A3B

20.6 GB22.9 GB file

32K 20.9 GB · 128K 21.9 GB

Q4_K_S

Qwen3 32B

19.1 GB18.8 GB file

32K 24.1 GB · 128K —

Qwen3.6 35B A3B

20.6 GB20.9 GB file

32K 20.9 GB · 128K 21.9 GB

Q4_K_L

Qwen3 32B

20.7 GB20.3 GB file

32K 25.7 GB · 128K —

Qwen3.6 35B A3B

22.4 GB22.7 GB file

32K 22.7 GB · 128K 23.7 GB

Q5_0

Qwen3 32B

21.1 GB22.6 GB file

32K 26.1 GB · 128K —

Qwen3.6 35B A3B

22.9 GB24.1 GB file

32K 23.1 GB · 128K 24.1 GB

Q5_1

Qwen3 32B

not listed

Qwen3.6 35B A3B

25.1 GB26.1 GB file

32K 25.4 GB · 128K 26.4 GB

Q5_K_S

Qwen3 32B

23.2 GB22.6 GB file

32K 28.2 GB · 128K —

Qwen3.6 35B A3B

25.1 GB24.9 GB file

32K 25.4 GB · 128K 26.4 GB

Q5_K_L

Qwen3 32B

24.4 GB23.7 GB file

32K 29.4 GB · 128K —

Qwen3.6 35B A3B

26.5 GB26.2 GB file

32K 26.7 GB · 128K 27.7 GB

BF16

Qwen3 32B

66.2 GB65.5 GB file

32K 71.2 GB · 128K —

Qwen3.6 35B A3B

72.3 GB69.4 GB file

32K 72.5 GB · 128K 73.6 GB

How to run each

Qwen3 32B

Ollama · Q4_K_M

$ollama run hf.co/Qwen/Qwen3-32B-GGUF:Q4_K_M

All ways to run Qwen3 32B →

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 Qwen3 32B and Qwen3.6 35B A3B
Spec	Qwen3 32B	Qwen3.6 35B A3B
Publisher	Alibaba	Alibaba
Parameters	32.8B	36.0B
Active parameters	—	4.7B per token
Architecture	Qwen3ForCausalLM	Qwen3_5MoeForConditionalGeneration
Context	40K tokens	256K tokens
Modalities	Chat, Function-calling	Vision, Function-calling
License	Apache 2.0	Apache 2.0
Released	Apr 2025	Apr 2026

Frequently Asked Questions

Which is better, Qwen3 32B or Qwen3.6 35B A3B?

Qwen3.6 35B A3B leads llmrun Score 106.8 to 98.6; both fit 24 GB at Q4_K_M; Qwen3.6 35B A3B is 4.7× faster on RTX 4090 (~151 vs ~32 tok/s). Choose Qwen3 32B for fits a 16 GB GPU and also does chat; choose Qwen3.6 35B A3B for higher llmrun Score and stronger at science.

Which needs less VRAM, Qwen3 32B or Qwen3.6 35B A3B?

At Q4_K_M, Qwen3 32B requires 20.3 GB while Qwen3.6 35B A3B needs 22.0 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 Qwen3 32B (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 Qwen3 32B or Qwen3.6 35B A3B on a 16 GB GPU?

Qwen3 32B fits at IQ3_XXS; Qwen3.6 35B A3B fits at Q2_K.

Which has a longer context window, Qwen3 32B or Qwen3.6 35B A3B?

Qwen3 32B supports 40,960 tokens and Qwen3.6 35B A3B supports 262,144 tokens.