llmrun

GPT OSS 20B vs Qwen3 32B

Qwen3 32B leads llmrun Score 98.6 to 96.4 (ranges overlap); both fit 24 GB at Q4_K_M; GPT OSS 20B is 5.9× faster on RTX 4090 (~190 vs ~32 tok/s).

Model A · OpenAI

GPT OSS 20B
96.4llmrun Score

20.9B · 4.2B active · 128K context · Apache 2.0 · Aug 2025

ChatFunctions

Model B · Alibaba

Qwen3 32B
98.6llmrun Score

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

ChatFunctions

Which should you choose?

Choose GPT OSS 20B if you want…

  • Stronger at coding

    101.9 vs 93.2

  • Fits a 12 GB GPU

    IQ4_XS · 11.8 GB; Qwen3 32B needs 12 GB at its smallest quant

  • 5.9× faster on RTX 4090

    ~190 vs ~32 tok/s

  • Lighter on memory

    12.9 vs 20.3 GB at Q4_K_M

  • Longer context window

    128K vs 40K tokens

  • Newer release

    Aug 2025 vs Apr 2025

Choose Qwen3 32B if you want…

  • Higher llmrun Score

    98.6 vs 96.4, ranges overlap

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

GPT OSS 20B

IQ2_M · ~103 tok/s

7.6 GB · up to 32Kfits

Qwen3 32B

Doesn't fit

smallest quant needs 12 GB

12 GB

RTX 3060 12GB · 12 GB tier

GPT OSS 20B

IQ4_XS · ~89 tok/s

11.8 GB · up to 16Kbetter quant

Qwen3 32B

IQ2_XXS · ~24 tok/s

12 GB · up to 16K

16 GB

RTX 5060 Ti 16GB · 16 GB tier

GPT OSS 20B

Q4_K_M · ~98 tok/s

13.1 GB · up to 128Kmore headroom

Qwen3 32B

IQ3_XXS · ~22 tok/s

15.7 GB · up to 16K

24 GBreference

RTX 4090 · 24 GB tier

GPT OSS 20B

Q4_K_M · ~190 tok/s

13.1 GB · up to 128Kfaster

Qwen3 32B

Q4_K_M · ~32 tok/s

22.6 GB · up to 16K

32 GB

RTX 5090 · 32 GB tier

GPT OSS 20B

Q4_K_M · ~282 tok/s

13.1 GB · up to 128Kfaster

Qwen3 32B

Q4_K_M · ~57 tok/s

22.6 GB · up to 40K

48 GB

RTX A6000 · 48 GB tier

GPT OSS 20B

Q4_K_M · ~154 tok/s

13.1 GB · up to 128Kfaster

Qwen3 32B

Q4_K_M · ~25 tok/s

22.6 GB · up to 40K

Mac 32 GB

Mac Mini M4 · Macs

GPT OSS 20B

Q4_K_M · ~28 tok/s

13.1 GB · up to 128Kfaster

Qwen3 32B

Q4_K_M · ~4 tok/s

22.6 GB · up to 40K

Mac 64 GB

Mac Studio M4 Max · Macs

GPT OSS 20B

Q4_K_M · ~86 tok/s

13.1 GB · up to 128Kfaster

Qwen3 32B

Q4_K_M · ~19 tok/s

22.6 GB · up to 40K

Mac 128 GB

Mac Studio M4 Max · Macs

GPT OSS 20B

Q4_K_M · ~86 tok/s

13.1 GB · up to 128Kfaster

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

GPT OSS 20B

96.493–100

Qwen3 32B

98.696–102

Coding

GPT OSS 20B

101.993–111

Qwen3 32B

93.287–99

Science

GPT OSS 20B

93.186–101

Qwen3 32B

96.089–104

Reasoning

GPT OSS 20B

91.383–100

Qwen3 32B

91.583–100

GPT OSS 20B · #69 of 106 open models · #16 of 36 that fit 24 GB

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

Benchmarks

6 shared boards: GPT OSS 20B leads 3, Qwen3 32B leads 3 · Benchmarks imported Nov 2026

GPQA Diamond

GPT OSS 20B

60.8%#44/100 open

IndependentEpoch AI · Aug 2025

Qwen3 32B

65.7%#39/100 open

IndependentEpoch AI · Apr 2025

AIME 2024/2025

GPT OSS 20B

65.3%#36/88 open

IndependentEpoch AI · Aug 2025

Qwen3 32B

66.9%#33/88 open

IndependentEpoch AI · Apr 2025

SciCode

GPT OSS 20B

38.9%#41/72 open

Lab-reportedEpoch AI · Aug 2025

Qwen3 32B

35.4%#54/72 open

Lab-reportedEpoch AI · Apr 2025

CritPt

GPT OSS 20B

1.4%#36/84 open

Lab-reportedEpoch AI · Aug 2025

Qwen3 32B

0.3%#50/84 open

Lab-reportedEpoch AI · Apr 2025

DTBench

GPT OSS 20B

68.0%#36/70 open

Lab-reportedEpoch AI · Aug 2025

Qwen3 32B

67.5%#37/70 open

Lab-reportedEpoch AI · Apr 2025

LMCA

GPT OSS 20B

14.5%#45/56 open

Lab-reportedEpoch AI · Aug 2025

Qwen3 32B

17.3%#39/56 open

Lab-reportedEpoch AI · Apr 2025

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

GPT OSS 20B

1317.3#98/188 open

ArenaLMArena · Oct 2026

Qwen3 32B

1346.8#80/188 open

ArenaLMArena · Oct 2026

Only GPT OSS 20B (4)

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

GPT OSS 20B

9.3 GB11.5 GB file

32K 9.8 GB · 128K 11.5 GB

Qwen3 32B

14.6 GB12.3 GB file

32K 19.6 GB · 128K —

Q3_K_S

GPT OSS 20B

9.5 GB11.5 GB file

32K 10.0 GB · 128K 11.7 GB

Qwen3 32B

15.0 GB14.4 GB file

32K 20.0 GB · 128K —

Q3_K_M

GPT OSS 20B

10.6 GB11.5 GB file

32K 11.1 GB · 128K 12.8 GB

Qwen3 32B

16.6 GB16.0 GB file

32K 21.6 GB · 128K —

Q4_0

GPT OSS 20B

10.8 GB11.5 GB file

32K 11.3 GB · 128K 13.0 GB

Qwen3 32B

17.0 GB18.7 GB file

32K 22.1 GB · 128K —

Q4_K_M

GPT OSS 20B

12.9 GB11.6 GB file

32K 13.4 GB · 128K 15.1 GB

Qwen3 32B

20.3 GB19.8 GB file

32K 25.3 GB · 128K —

Q5_K_M

GPT OSS 20B

15.3 GB11.7 GB file

32K 15.8 GB · 128K 17.5 GB

Qwen3 32B

24.0 GB23.2 GB file

32K 29.0 GB · 128K —

Q6_K

GPT OSS 20B

17.6 GB12.0 GB file

32K 18.1 GB · 128K 19.8 GB

Qwen3 32B

27.7 GB26.9 GB file

32K 32.7 GB · 128K —

Q8_0

GPT OSS 20B

21.3 GB~20.9 GB file

32K 21.8 GB · 128K 23.5 GB

Qwen3 32B

33.4 GB34.8 GB file

32K 38.4 GB · 128K —

19 more quants

IQ2_XXS

GPT OSS 20B

6.1 GB~5.8 GB file

32K 6.6 GB · 128K 8.3 GB

Qwen3 32B

9.7 GB9.3 GB file

32K 14.7 GB · 128K —

IQ2_XS

GPT OSS 20B

6.7 GB~6.3 GB file

32K 7.2 GB · 128K 8.9 GB

Qwen3 32B

10.5 GB10.0 GB file

32K 15.5 GB · 128K —

IQ2_S

GPT OSS 20B

6.9 GB~6.5 GB file

32K 7.4 GB · 128K 9.1 GB

Qwen3 32B

10.9 GB10.5 GB file

32K 15.9 GB · 128K —

IQ2_M

GPT OSS 20B

7.4 GB~7.1 GB file

32K 7.9 GB · 128K 9.6 GB

Qwen3 32B

11.7 GB11.6 GB file

32K 16.7 GB · 128K —

IQ3_XXS

GPT OSS 20B

8.5 GB11.6 GB file

32K 9.0 GB · 128K 10.7 GB

Qwen3 32B

13.3 GB13.0 GB file

32K 18.4 GB · 128K —

Q2_K_S

GPT OSS 20B

8.7 GB12.1 GB file

32K 9.2 GB · 128K 10.9 GB

Qwen3 32B

13.7 GB11.5 GB file

32K 18.8 GB · 128K —

IQ3_XS

GPT OSS 20B

9.0 GB11.6 GB file

32K 9.5 GB · 128K 11.2 GB

Qwen3 32B

14.2 GB13.7 GB file

32K 19.2 GB · 128K —

IQ3_S

GPT OSS 20B

9.3 GB12.1 GB file

32K 9.8 GB · 128K 11.5 GB

Qwen3 32B

14.6 GB14.4 GB file

32K 19.6 GB · 128K —

IQ3_M

GPT OSS 20B

9.8 GB11.6 GB file

32K 10.3 GB · 128K 12.0 GB

Qwen3 32B

15.4 GB14.9 GB file

32K 20.4 GB · 128K —

Q3_K_L

GPT OSS 20B

11.1 GB11.5 GB file

32K 11.6 GB · 128K 13.3 GB

Qwen3 32B

17.4 GB17.3 GB file

32K 22.5 GB · 128K —

IQ4_XS

GPT OSS 20B

11.6 GB11.6 GB file

32K 12.1 GB · 128K 13.8 GB

Qwen3 32B

18.3 GB17.7 GB file

32K 23.3 GB · 128K —

IQ4_NL

GPT OSS 20B

12.1 GB11.6 GB file

32K 12.6 GB · 128K 14.3 GB

Qwen3 32B

19.1 GB18.7 GB file

32K 24.1 GB · 128K —

Q4_1

GPT OSS 20B

12.1 GB11.6 GB file

32K 12.6 GB · 128K 14.3 GB

Qwen3 32B

19.1 GB20.6 GB file

32K 24.1 GB · 128K —

Q4_K_S

GPT OSS 20B

12.1 GB11.6 GB file

32K 12.6 GB · 128K 14.3 GB

Qwen3 32B

19.1 GB18.8 GB file

32K 24.1 GB · 128K —

Q4_K_L

GPT OSS 20B

13.2 GB11.9 GB file

32K 13.7 GB · 128K 15.4 GB

Qwen3 32B

20.7 GB20.3 GB file

32K 25.7 GB · 128K —

Q5_0

GPT OSS 20B

not listed

Qwen3 32B

21.1 GB22.6 GB file

32K 26.1 GB · 128K —

Q5_K_S

GPT OSS 20B

14.8 GB11.7 GB file

32K 15.3 GB · 128K 17.0 GB

Qwen3 32B

23.2 GB22.6 GB file

32K 28.2 GB · 128K —

Q5_K_L

GPT OSS 20B

15.5 GB11.9 GB file

32K 16.0 GB · 128K 17.7 GB

Qwen3 32B

24.4 GB23.7 GB file

32K 29.4 GB · 128K —

BF16

GPT OSS 20B

42.2 GB~41.8 GB file

32K 42.7 GB · 128K 44.4 GB

Qwen3 32B

66.2 GB65.5 GB file

32K 71.2 GB · 128K —

How to run each

Specifications

Specifications of GPT OSS 20B and Qwen3 32B
SpecGPT OSS 20BQwen3 32B
PublisherOpenAIAlibaba
Parameters20.9B32.8B
Active parameters4.2B per token—
ArchitectureGptOssForCausalLMQwen3ForCausalLM
Context128K tokens40K tokens
ModalitiesChat, Function-callingChat, Function-calling
LicenseApache 2.0Apache 2.0
ReleasedAug 2025Apr 2025

Frequently Asked Questions

Which is better, GPT OSS 20B or Qwen3 32B?

Qwen3 32B leads llmrun Score 98.6 to 96.4 (ranges overlap); both fit 24 GB at Q4_K_M; GPT OSS 20B is 5.9× faster on RTX 4090 (~190 vs ~32 tok/s). Choose GPT OSS 20B for stronger at coding and fits a 12 GB GPU; choose Qwen3 32B for higher llmrun Score.

Which needs less VRAM, GPT OSS 20B or Qwen3 32B?

At Q4_K_M, GPT OSS 20B requires 12.9 GB while Qwen3 32B needs 20.3 GB, making GPT OSS 20B the easier model to run on your local setup.

Which is faster on RTX 4090?

Estimated decode speed on RTX 4090 is about 190 tok/s for GPT OSS 20B (Q4_K_M) and 32 tok/s for Qwen3 32B (Q4_K_M), so GPT OSS 20B is faster. Estimates, ±20%.

Can I run GPT OSS 20B or Qwen3 32B on a 16 GB GPU?

GPT OSS 20B fits at Q4_K_M; Qwen3 32B fits at IQ3_XXS.

Which has a longer context window, GPT OSS 20B or Qwen3 32B?

GPT OSS 20B supports 131,072 tokens and Qwen3 32B supports 40,960 tokens.

GPT OSS 20B vs Qwen3 32B — VRAM & GPU Comparison | llmrun